Tool-Use on AI Knowledge Base

Building with the Claude API

Mon, 01 Jan 0001 00:00:00 +0000

The most comprehensive free course on building with Claude’s API — 21 lessons covering everything from basic API calls to tool use, structured outputs, and agent patterns. This is Anthropic’s flagship developer course and the definitive companion to the Claude API documentation in this knowledge base. If you’re building production applications with Claude, this course provides the hands-on practice that documentation alone cannot. Take this alongside the Claude API Essentials learning path.

OpenAI API Essentials

Mon, 01 Jan 0001 00:00:00 +0000

Learn the OpenAI API from first request to advanced features. Covers Chat Completions, function calling, structured outputs, streaming, vision, reasoning models, and embeddings.

Claude API Essentials

Mon, 01 Jan 0001 00:00:00 +0000

Learn the Anthropic API from first principles. Covers the Messages API, tool use, streaming, structured outputs, extended thinking, and cost optimization.

MCP Fundamentals

Mon, 01 Jan 0001 00:00:00 +0000

Go from zero to a solid understanding of the Model Context Protocol. This path covers the core architecture, primitives (tools, resources, prompts), transport mechanisms, and how clients and servers interact.

By the end you’ll understand the MCP mental model well enough to evaluate MCP servers, build simple integrations, and read the specification confidently.

Building MCP Servers

Mon, 01 Jan 0001 00:00:00 +0000

Learn to build production-quality MCP servers. This path takes you from a basic server implementation through transport selection, security, and publishing to the registry.

Prerequisites: Complete the MCP Fundamentals path first to understand the protocol architecture.

Functions, Tools and Agents with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Deepens the LangChain introduction with focus on function calling, tool use, and agent patterns — the building blocks of agentic AI applications. Covers OpenAI’s function calling API, LangChain tool abstractions, and conversational agents. Take this after the LangChain intro to understand how agents actually work under the hood.

Agent SDK — Overview

Mon, 01 Jan 0001 00:00:00 +0000

Introduction to Anthropic’s Agent SDK for building custom AI agents with tool use, MCP, and sub-agents.

Tool Use — Overview

Mon, 01 Jan 0001 00:00:00 +0000

How Claude calls external tools and functions — the foundation for building agentic systems.

Agent SDK Deep Dive

Mon, 01 Jan 0001 00:00:00 +0000

Build custom AI agents with the Anthropic Agent SDK. Covers both TypeScript and Python SDKs, custom tools, MCP integration, sub-agents, streaming, and production deployment.

Prerequisites: Familiarity with the Claude API (complete Claude API Essentials first).

Multi-Agent Systems

Mon, 01 Jan 0001 00:00:00 +0000

Explore how to build systems with multiple cooperating AI agents. Compare approaches across eight frameworks: Anthropic Agent SDK, OpenAI Agents SDK, CrewAI, LangGraph, Google ADK, Microsoft Agent Framework, AutoGen, and OpenAI Symphony — plus the A2A protocol for cross-platform agent communication.

Each framework embodies a different orchestration paradigm: delegation, handoffs, crews, state machines, workflow agents, enterprise graphs, group chat, and autonomous work management. Understanding the design space helps you pick the right tool for your architecture.

Agents Course

Mon, 01 Jan 0001 00:00:00 +0000

Hugging Face’s comprehensive agents course — covers agent fundamentals, tool use, ReAct pattern, multi-agent systems, and building production agents with open-source models. The open-source counterpart to Anthropic’s agent courses: where Anthropic teaches you to build agents with Claude, Hugging Face teaches you to build agents with any open model. Essential if you’re evaluating open vs. proprietary agent architectures.

Implement Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

Step-by-step guide to implementing the tool use loop: define tools, handle tool_use responses, send tool_result.

Structured Outputs

Mon, 01 Jan 0001 00:00:00 +0000

Get reliable JSON outputs from Claude using tool_use or constrained decoding.

01 Intro Basics

Mon, 01 Jan 0001 00:00:00 +0000

Learn the basics of fine-tuning LLMs with Mistral AI’s API and open-source tools for optimized performance

Action confirmations

Mon, 01 Jan 0001 00:00:00 +0000

Add Tools to Agents

Mon, 01 Jan 0001 00:00:00 +0000

Add tool calling capabilities to agents with automatic schema inference from Python functions.

Advanced Tool Features

Mon, 01 Jan 0001 00:00:00 +0000

Advanced Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

Agent Capabilities

Mon, 01 Jan 0001 00:00:00 +0000

Understand the five ways to extend CrewAI agents: Tools, MCPs, Apps, Skills, and Knowledge.

Agent definitions

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to define an agent’s instructions, model, tools, and local context in the OpenAI Agents SDK.

Agentic IDEs and CLIs

Mon, 01 Jan 0001 00:00:00 +0000

Use Pinecone with agentic IDEs and CLIs like Claude Code, Gemini CLI, Cursor, and more.

Agentic Multi-Stage RAG with Cohere Tools API

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to build a powerful, multi-stage agent with the Cohere platform.

Agentic or Tool use

Mon, 01 Jan 0001 00:00:00 +0000

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Configure agent instructions, tools, guardrails, memory, and streaming behavior.

Agents & Conversations

Mon, 01 Jan 0001 00:00:00 +0000

Agents & Conversations API: Create, manage agents with tools, and handle interactive conversations with persistent history

Agents Function Calling

Mon, 01 Jan 0001 00:00:00 +0000

Agents use tools and function calling to perform tasks, with built-in and customizable options

Agents Handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Agents Handoffs enable seamless task delegation and workflow automation between multiple agents with diverse tools and capabilities

Agents Introduction

Mon, 01 Jan 0001 00:00:00 +0000

Introduction to Mistral’s agent system — autonomous task execution with tools, state persistence, connectors (code interpreter, web search), and multi-agent collaboration.

AI Mind Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘AIMindTool’ is designed to query data sources in natural language.

An Overview of Tool Use with Cohere

Mon, 01 Jan 0001 00:00:00 +0000

Learn when to use leverage multi-step tool use in your workflows.

Anthropic compatibility

Mon, 01 Jan 0001 00:00:00 +0000

Use Anthropic SDKs with Fireworks, and understand the supported surface for the Anthropic-compatible Messages API.

API & Integrations

Mon, 01 Jan 0001 00:00:00 +0000

Manage clusters programmatically with CLI, REST API, Terraform, and third-party tools

Apify Actors

Mon, 01 Jan 0001 00:00:00 +0000

‘ApifyActorsTool’ lets you call Apify Actors to provide your CrewAI workflows with web scraping, crawling, data extraction, and web automation capabilities.

Apply patch

Mon, 01 Jan 0001 00:00:00 +0000

Allow models to propose structured diffs that your integration applies.

Arxiv Paper Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ArxivPaperTool’ searches arXiv for papers matching a query and optionally downloads PDFs.

Assistants Code Interpreter

Mon, 01 Jan 0001 00:00:00 +0000

Allow assistants to run Python code with the Code Interpreter tool.

Assistants File Search

Mon, 01 Jan 0001 00:00:00 +0000

Use File Search as a built-in RAG tool for assistants.

Assistants Function Calling

Mon, 01 Jan 0001 00:00:00 +0000

Use function calling to extend assistants with your own tools.

Authentication

Mon, 01 Jan 0001 00:00:00 +0000

Bash Tool

Mon, 01 Jan 0001 00:00:00 +0000

The bash tool gives Claude direct shell access to execute commands, making it one of the most powerful and dangerous built-in tools available. It enables agents to run scripts, install packages, manage files, and interact with system utilities, forming the backbone of coding and DevOps automation workflows. Be deliberate about sandboxing: without proper isolation, Claude can execute arbitrary commands with the permissions of the host process. Start with a restrictive allowlist of commands and expand carefully, and always prefer higher-level tools like the text editor for file modifications where available rather than piping through sed or echo.

Basic usage of tool use (function calling)

Mon, 01 Jan 0001 00:00:00 +0000

Overview of Cohere’s tool use system for building agentic workflows — with native citation support that links tool results back to generated text.

Bedrock Invoke Agent Tool

Mon, 01 Jan 0001 00:00:00 +0000

Enables CrewAI agents to invoke Amazon Bedrock Agents and leverage their capabilities within your workflows

Bedrock Knowledge Base Retriever

Mon, 01 Jan 0001 00:00:00 +0000

Retrieve information from Amazon Bedrock Knowledge Bases using natural language queries

Best Practices

Mon, 01 Jan 0001 00:00:00 +0000

This guide distills hard-won patterns for building reliable agent skills that perform well across diverse user inputs and edge cases. Pay particular attention to the guidance on error handling within skill execution and how to design tool descriptions that minimize misuse by the model. A common mistake is writing overly generic skill descriptions, which leads Claude to invoke skills in inappropriate contexts and degrades overall agent quality. Start here after completing the skills quickstart to refine your implementations before deploying to production.

Bienvenue to Mistral AI Documentation

Mon, 01 Jan 0001 00:00:00 +0000

Mistral AI offers open-source and commercial LLMs, APIs, and tools for developers and enterprises to build AI-powered applications

Brave Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘BraveSearchTool’ is designed to search the internet using the Brave Search API.

Bright Data Tools

Mon, 01 Jan 0001 00:00:00 +0000

Bright Data integrations for SERP search, Web Unlocker scraping, and Dataset API.

Browserbase Web Loader

Mon, 01 Jan 0001 00:00:00 +0000

Browserbase is a developer platform to reliably run, manage, and monitor headless browsers.

Build A Tool Using Agent

Mon, 01 Jan 0001 00:00:00 +0000

Built-in Tools

Mon, 01 Jan 0001 00:00:00 +0000

Calendar Agent with Native Multi Step Tool

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to use cohere Chat API with list_calendar_events and create_calendar_event tools to book appointments.

Call tools

Mon, 01 Jan 0001 00:00:00 +0000

How to call tools with W&B Inference

Channels reference

Mon, 01 Jan 0001 00:00:00 +0000

Build an MCP server that pushes webhooks, alerts, and chat messages into a Claude Code session. Reference for the channel contract: capability declaration, notification events, reply tools, sender gating, and permission relay.

ChatGPT Developer mode

Mon, 01 Jan 0001 00:00:00 +0000

Full MCP client access for apps and tools.

Citations for tool use (function calling)

Mon, 01 Jan 0001 00:00:00 +0000

Guide on accessing and utilizing citations generated by the Cohere Chat endpoint for tool use. It covers both non-streaming and streaming modes (API v2).

Claude Api Skill

Mon, 01 Jan 0001 00:00:00 +0000

Claude Code overview

Mon, 01 Jan 0001 00:00:00 +0000

Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and browser.

Claude Code Plugin

Mon, 01 Jan 0001 00:00:00 +0000

Install the official Pinecone plugin for Claude Code to get skills, MCP tools, and slash commands for managing indexes and building AI applications.

Code Docs RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘CodeDocsSearchTool’ is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within code documentation.

Code Execution

Mon, 01 Jan 0001 00:00:00 +0000

Sandboxed code execution in AutoGen: Docker-based and local executors for running agent-generated code safely.

Code Execution Tool

Mon, 01 Jan 0001 00:00:00 +0000

The code execution tool lets Claude run Python code in a sandboxed environment during a conversation, enabling data analysis, mathematical computation, and rapid prototyping without requiring external infrastructure. This is particularly valuable for tasks where Claude needs to verify its own reasoning through computation rather than relying on mental arithmetic or approximation. Note that the sandbox has limited package availability and no network access, so complex data science workflows may hit dependency walls. Use this tool when you need deterministic computation results embedded directly in Claude’s response rather than asking the user to run code separately.

Code Interpreter

Mon, 01 Jan 0001 00:00:00 +0000

The ‘CodeInterpreterTool’ is a powerful tool designed for executing Python 3 code within a secure, isolated environment.

Code Interpreter

Mon, 01 Jan 0001 00:00:00 +0000

Allow models to write and run Python to solve problems.

Coding

Mon, 01 Jan 0001 00:00:00 +0000

Mistral AI offers Codestral for code generation & FIM, and Devstral for agentic tool use in software development, with integrations for IDEs and frameworks

Coding Tools

Mon, 01 Jan 0001 00:00:00 +0000

Use AGENTS.md to guide coding agents and IDEs across your CrewAI projects.

Cohere Chat on LangChain (Integration Guide)

Mon, 01 Jan 0001 00:00:00 +0000

Integrate Cohere with LangChain to build applications using Cohere’s models and LangChain tools.

Cohere Tools on LangChain (Integration Guide)

Mon, 01 Jan 0001 00:00:00 +0000

Explore code examples for multi-step and single-step tool usage in chatbots, harnessing internet search and vector storage.

Cohere's Command A Reasoning Model

Mon, 01 Jan 0001 00:00:00 +0000

Command A Reasoning excels in tool use, agentic workflows, and complex problem-solving. It has 111 billion parameters and a 256k context length.

Cohere's Command R+ Model

Mon, 01 Jan 0001 00:00:00 +0000

Command R+ is Cohere’s optimized for conversational interaction and long-context tasks, best suited for complex RAG workflows and multi-step tool use.

Cohere's Command R7B Model

Mon, 01 Jan 0001 00:00:00 +0000

Command R7B is the smallest, fastest, and final model in our R family of enterprise-focused large language models. It excels at RAG, tool use, and agents.

Command A

Mon, 01 Jan 0001 00:00:00 +0000

Command A is a performant mode good at tool use, RAG, agents, and multilingual use cases. It has 111 billion parameters and a 256k context length.

Common Tools

Mon, 01 Jan 0001 00:00:00 +0000

Compare model performance using the Evaluation Playground

Mon, 01 Jan 0001 00:00:00 +0000

Compare and evaluate model performance without code using Weave’s interactive playground, running evaluations with custom datasets and LLM judges to test system prompts, models, and scoring criteria in a visual interface.

Compare traces and other logged information

Mon, 01 Jan 0001 00:00:00 +0000

Visually compare and diff code, traces, prompts, models, and configurations

Composio Tool

Mon, 01 Jan 0001 00:00:00 +0000

Composio provides 250+ production-ready tools for AI agents with flexible authentication management.

Computer use

Mon, 01 Jan 0001 00:00:00 +0000

Enable models to interact with computer interfaces — clicking, typing, and navigating applications via screenshots, creating agents that can operate any software.

Computer Use Tool

Mon, 01 Jan 0001 00:00:00 +0000

Computer use enables Claude to interact with desktop environments through screenshots, mouse clicks, and keyboard input, effectively giving it the ability to operate any GUI application. This opens up automation for legacy software, web applications behind authentication, and workflows that lack APIs. Be aware that computer use is significantly slower and less reliable than API-based tool calling – treat it as a last resort for tasks that genuinely have no programmatic interface. Start with constrained screen regions and simple click-type sequences before attempting complex multi-window workflows, and always implement human-in-the-loop checkpoints for destructive actions.

Conditional Workflow

Mon, 01 Jan 0001 00:00:00 +0000

Adapt to different tasks by conditionally navigating to various LLMs and tools.

Connect Claude Code to tools via MCP

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to connect Claude Code to your tools with the Model Context Protocol.

Connect to remote MCP Servers

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to connect Claude to remote MCP servers and extend its capabilities with internet-hosted tools and data sources

Connecting to Multiple MCP Servers

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use MCPServerAdapter in CrewAI to connect to multiple MCP servers simultaneously and aggregate their tools.

Connectors and MCP servers

Mon, 01 Jan 0001 00:00:00 +0000

Use remote MCP servers and OpenAI-maintained connectors for popular services to give models new capabilities.

Connectors Overview

Mon, 01 Jan 0001 00:00:00 +0000

Connectors enable Agents and users to access tools like websearch, code interpreter, image generation, and document library on demand

Create and manage saved views

Mon, 01 Jan 0001 00:00:00 +0000

Customize how you interact with traced function calls and evaluations

Create Custom Tools

Mon, 01 Jan 0001 00:00:00 +0000

Comprehensive guide on crafting, using, and managing custom tools within the CrewAI framework, including new functionalities and error handling.

CrewAI Run Automation Tool

Mon, 01 Jan 0001 00:00:00 +0000

Enables CrewAI agents to invoke CrewAI Platform automations and leverage external crew services within your workflows.

CSV RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘CSVSearchTool’ is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within a CSV file’s content.

Custom Tools

Mon, 01 Jan 0001 00:00:00 +0000

Custom tools are how you give your agent the ability to take actions beyond conversation – calling APIs, querying databases, executing code, or interacting with any external system. Focus on how the tool’s JSON schema definition directly affects the model’s ability to invoke it correctly; poorly described parameters are the most common source of tool invocation failures. Pay special attention to error handling within tool implementations, since unhandled exceptions will surface as opaque failures in the agentic loop. If your tools need to call external MCP servers instead, read the MCP integration guide as an alternative approach.

Custom Tools for ADK

Mon, 01 Jan 0001 00:00:00 +0000

Customize Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to customize deep agents with system prompts, tools, subagents, and more

Customize Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to customize deep agents with system prompts, tools, subagents, and more

DALL-E Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DallETool’ is a powerful tool designed for generating images from textual descriptions.

Databricks SQL Query Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DatabricksQueryTool’ executes SQL queries against Databricks workspace tables.

Debugging

Mon, 01 Jan 0001 00:00:00 +0000

A comprehensive guide to debugging Model Context Protocol (MCP) integrations

Deferred Tools

Mon, 01 Jan 0001 00:00:00 +0000

Define and log attributes

Mon, 01 Jan 0001 00:00:00 +0000

Use attributes to add meta data to your traces and evaluations.

Define Tools

Mon, 01 Jan 0001 00:00:00 +0000

Developer quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use the OpenAI API to generate human-like responses to natural language prompts, analyze images with computer vision, use powerful built-in tools, and more.

Directory RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DirectorySearchTool’ is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within a directory’s content.

Directory Read

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DirectoryReadTool’ is a powerful utility designed to provide a comprehensive listing of directory contents.

DOCX RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DOCXSearchTool’ is a RAG tool designed for semantic searching within DOCX documents.

Enterprise

Mon, 01 Jan 0001 00:00:00 +0000

The enterprise skills guide addresses deployment concerns that only surface at organizational scale: access control, audit logging, skill versioning, and multi-tenant isolation. Focus on the permission model and how skill execution contexts are sandboxed — getting this wrong can expose one tenant’s data to another. A key pitfall is treating enterprise skill deployment as a simple extension of single-user patterns; the authentication and authorization layers add meaningful complexity to the skill lifecycle. Read this after the quickstart and best practices guides, as it assumes familiarity with core skill mechanics.

EXA Search Web Loader

Mon, 01 Jan 0001 00:00:00 +0000

The ‘EXASearchTool’ is designed to perform a semantic search for a specified query from a text’s content across the internet.

File Read

Mon, 01 Jan 0001 00:00:00 +0000

The ‘FileReadTool’ is designed to read files from the local file system.

File search

Mon, 01 Jan 0001 00:00:00 +0000

Built-in file search tool that lets models search uploaded files for relevant information before generating responses, providing managed RAG without external infrastructure.

File Write

Mon, 01 Jan 0001 00:00:00 +0000

The ‘FileWriterTool’ is designed to write content to files.

Fine Grained Tool Streaming

Mon, 01 Jan 0001 00:00:00 +0000

Fine-grained tool streaming gives you granular control over how tool call arguments and results are delivered incrementally, which is essential for building responsive UIs on top of agentic workflows. Focus on the event types and their ordering — understanding the difference between input_json delta events and tool_result blocks determines how you parse partial tool invocations. One subtle pitfall is assuming tool arguments arrive as valid JSON at each delta; you need to buffer and parse only after the tool use block is complete. Read this after the general streaming guide to layer tool-specific streaming behavior on top of basic SSE handling.

Firecrawl Crawl Website

Mon, 01 Jan 0001 00:00:00 +0000

The ‘FirecrawlCrawlWebsiteTool’ is designed to crawl and convert websites into clean markdown or structured data.

Firecrawl Scrape Website

Mon, 01 Jan 0001 00:00:00 +0000

The ‘FirecrawlScrapeWebsiteTool’ is designed to scrape websites and convert them into clean markdown or structured data.

Function calling

Mon, 01 Jan 0001 00:00:00 +0000

Function calling with Mistral models — integrate external tools for dynamic, data-driven responses using JSON Schema tool definitions.

Function calling

Mon, 01 Jan 0001 00:00:00 +0000

Learn how function calling enables large language models to connect to external data and systems.

Function Calling

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to get LLMs to respond to queries with named functions and structured arguments.

Function Calling Fine-tuning

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to fine-tune models with function calling capabilities using Together AI.

Function Tools

Mon, 01 Jan 0001 00:00:00 +0000

Gemini CLI Extension

Mon, 01 Jan 0001 00:00:00 +0000

Install the official Pinecone extension for Gemini CLI to get skills and MCP tools for managing indexes and building AI applications.

Getting Started with Basic Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to work with Cohere’s basic tool use functionality.

Github Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘GithubSearchTool’ is designed to search websites and convert them into clean markdown or structured data.

Glossary

Mon, 01 Jan 0001 00:00:00 +0000

Glossary of key AI and LLM terms, including LLMs, text generation, tokens, MoE, RAG, fine-tuning, function calling, embeddings, and temperature

Google Serper Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SerperDevTool’ is designed to search the internet and return the most relevant results.

Handle Tool Calls

Mon, 01 Jan 0001 00:00:00 +0000

How Claude Code works

Mon, 01 Jan 0001 00:00:00 +0000

Understand the agentic loop, built-in tools, and how Claude Code interacts with your project.

How Tool Use Works

Mon, 01 Jan 0001 00:00:00 +0000

Human Input on Execution

Mon, 01 Jan 0001 00:00:00 +0000

Integrating CrewAI with human input during execution in complex decision-making processes and leveraging the full capabilities of the agent’s attributes and tools.

Hyperbrowser Load Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘HyperbrowserLoadTool’ enables web scraping and crawling using Hyperbrowser.

Image generation

Mon, 01 Jan 0001 00:00:00 +0000

Generate and edit images using DALL-E and GPT-4o’s built-in image generation capabilities as tools within the Responses API.

Integrating Embedding Models with Other Tools

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to integrate Cohere embeddings with open-source vector search engines for enhanced applications.

JSON RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘JSONSearchTool’ is designed to search JSON files and return the most relevant results.

LangChain Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘LangChainTool’ is a wrapper for LangChain tools and query engines.

Let Claude use your computer from the CLI

Mon, 01 Jan 0001 00:00:00 +0000

Enable computer use in the Claude Code CLI so Claude can open apps, click, type, and see your screen on macOS. Test native apps, debug visual issues, and automate GUI-only tools without leaving your terminal.

Linkup Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘LinkupSearchTool’ enables querying the Linkup API for contextual information.

LlamaIndex Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘LlamaIndexTool’ is a wrapper for LlamaIndex tools and query engines.

Local shell

Mon, 01 Jan 0001 00:00:00 +0000

Enable agents to run commands in a local shell.

Manage Tool Context

Mon, 01 Jan 0001 00:00:00 +0000

Map columns in datasets

Mon, 01 Jan 0001 00:00:00 +0000

Map columns in datasets to different names. This helps you align the column names in your dataset with the column names expected by the scorer.

MCP

Mon, 01 Jan 0001 00:00:00 +0000

MCP is an open standard protocol for seamless AI model integration with data sources and tools

Mcp Connector

Mon, 01 Jan 0001 00:00:00 +0000

The MCP Connector is the primary mechanism for giving Claude direct access to external tools and data sources through the Model Context Protocol within API calls. Focus on how connector configuration differs from local MCP server setup — the connector handles transport, authentication, and tool discovery on Anthropic’s infrastructure rather than your own. A common pitfall is neglecting to scope tool permissions tightly, which can lead to unexpected token consumption when Claude explores available tools. Read this alongside the remote MCP servers guide to understand the full picture of hosted versus self-managed MCP integrations.

MCP Inspector

Mon, 01 Jan 0001 00:00:00 +0000

In-depth guide to using the MCP Inspector for testing and debugging Model Context Protocol servers

MCP Servers as Tools in CrewAI

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to integrate MCP servers as tools in your CrewAI agents using the crewai-tools library.

MCP tools

Mon, 01 Jan 0001 00:00:00 +0000

MCP Tools

Mon, 01 Jan 0001 00:00:00 +0000

Load additional tools from MCP (Model Context Protocol) servers

MDX RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘MDXSearchTool’ is designed to search MDX files and return the most relevant results.

Memory Tool

Mon, 01 Jan 0001 00:00:00 +0000

The memory tool allows Claude to persist information across conversation sessions, enabling agents to maintain user preferences, project context, and learned patterns over time. This bridges the gap between stateless API calls and the continuity users expect from long-running assistant relationships. Focus on understanding what gets stored and how retrieval works, since overloading memory with low-value data degrades relevance of future recalls. Design your memory strategy around high-signal items like user corrections and workflow preferences rather than attempting to memorize entire conversation histories.

Merge Agent Handler Tool

Mon, 01 Jan 0001 00:00:00 +0000

Enables CrewAI agents to securely access third-party integrations like Linear, GitHub, Slack, and more through Merge’s Agent Handler platform

Metrics Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

MistralAI

Mon, 01 Jan 0001 00:00:00 +0000

Track and monitor MistralAI model calls with Weave’s automatic tracing, capturing chat completions, function calling, and model interactions for open-weight and commercial Mistral models.

MongoDB Vector Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘MongoDBVectorSearchTool’ performs vector search on MongoDB Atlas with optional indexing helpers.

Multi-Step Tool Use with Cohere

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to create a multi-step, tool-using AI agent with Cohere’s tool use functionality.

MultiOn Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘MultiOnTool’ empowers CrewAI agents with the capability to navigate and interact with the web through natural language instructions.

MySQL RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘MySQLSearchTool’ is designed to search MySQL databases and return the most relevant results.

NL2SQL Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘NL2SQLTool’ is designed to convert natural language to SQL queries.

OCR Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘OCRTool’ extracts text from local images or image URLs using an LLM with vision.

OpenAI compatibility

Mon, 01 Jan 0001 00:00:00 +0000

OpenAPI tools

Mon, 01 Jan 0001 00:00:00 +0000

Orchestration and handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to orchestrate multiple agents with handoffs and agents-as-tools in the OpenAI Agents SDK.

Overview

Mon, 01 Jan 0001 00:00:00 +0000

This overview introduces the agent skills framework, which provides a structured way to package and distribute reusable capabilities that Claude-based agents can invoke. Skills sit between raw tool definitions and full agent architectures, giving you a composable middle layer for common tasks like code review, PR creation, or domain-specific analysis. Start here before reading the individual tool docs to understand how skills orchestrate multiple tools into cohesive workflows. The key architectural decision is which capabilities to implement as standalone tools versus packaged skills, and this doc provides the mental model for making that choice.

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Monitor, evaluate, and optimize your CrewAI agents with comprehensive observability tools

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Leverage AI services, generate images, process vision, and build intelligent systems

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Automate workflows and integrate with external platforms and services

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Interact with cloud services, storage systems, and cloud-based AI platforms

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Connect to databases, vector stores, and data warehouses for comprehensive data access

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Read, write, and search through various file formats with CrewAI’s document processing tools

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Connect CrewAI agents with external automations and managed AI services

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Perform web searches, find repositories, and research information across the internet

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Extract data from websites and automate browser interactions with powerful scraping tools

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Oxylabs Scrapers

Mon, 01 Jan 0001 00:00:00 +0000

Oxylabs Scrapers allow to easily access the information from the respective sources. Please see the list of available sources below:

Parallel Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

Parallel Tools

Mon, 01 Jan 0001 00:00:00 +0000

Parameter types for tool use (function calling)

Mon, 01 Jan 0001 00:00:00 +0000

Guide on using structured outputs with tool parameters in the Cohere Chat API. Includes guide on supported parameter types and usage examples (API v2).

PDF Extractor with Native Multi Step Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to create an AI agent able to extract information from PDFs.

PDF RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘PDFSearchTool’ is designed to search PDF files and return the most relevant results.

PDF Text Writing Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘PDFTextWritingTool’ writes text to specific positions in a PDF, supporting custom fonts.

PG RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘PGSearchTool’ is designed to search PostgreSQL databases and return the most relevant results.

Programmatic Tool Calling

Mon, 01 Jan 0001 00:00:00 +0000

Programmatic tool calling lets you force Claude to invoke a specific tool rather than deciding autonomously whether to use one, which is essential for deterministic agentic workflows where you need guaranteed structured output on every turn. This is particularly useful when building pipelines that must always extract data into a schema or always query an external system before responding. Be aware that forcing a tool call changes Claude’s behavior around the rest of the response – it will not produce any text content before the forced tool invocation. Read the general tool-use guide first to understand the baseline calling conventions, then use this doc to layer in the deterministic control patterns.

Prompting Tools

Mon, 01 Jan 0001 00:00:00 +0000

This guide is the definitive reference for writing effective tool definitions that Claude can invoke reliably. Focus on how parameter descriptions and tool descriptions influence Claude’s decision about when and how to call each tool – vague descriptions lead to incorrect invocations or tool avoidance. A common mistake is defining too many tools in a single request, which degrades selection accuracy; the guide offers practical thresholds. If you are building agentic applications with Claude, read this before the broader tool use documentation, as well-crafted tool prompts are the foundation of reliable agent behavior.

Publish Custom Tools

Mon, 01 Jan 0001 00:00:00 +0000

How to build, package, and publish your own CrewAI-compatible tools to PyPI so any CrewAI user can install and use them.

Python SDK

Mon, 01 Jan 0001 00:00:00 +0000

Qdrant Vector Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

Semantic search capabilities for CrewAI agents using Qdrant vector database

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

This quickstart walks you through building your first agent skill end-to-end, from definition to invocation within a Claude-powered agent. Focus on the skill registration pattern and how the runtime discovers and exposes skills to the model — getting this wiring right is foundational for everything else. Be aware that the quickstart uses simplified error handling; production skills need retry logic and graceful degradation as covered in the best practices guide. Work through this hands-on before reading the enterprise or best practices docs to build concrete intuition first.

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build your first agent with the OpenAI Agents SDK, add tools and handoffs, and understand where to go next.

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Get started with Pinecone manually, with AI assistance, or with no-code tools.

RAG Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘RagTool’ is a dynamic knowledge base tool for answering questions using Retrieval-Augmented Generation.

Realtime API with MCP

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to configure MCP tools in the Realtime API and handle the resulting event flow.

Reasoning Capabilities

Mon, 01 Jan 0001 00:00:00 +0000

Reasoning models excel at tool use, agentic workflows, and complex problem-solving. This page provides a general overview of Cohere’s reasoning capalities.

Remote Mcp Servers

Mon, 01 Jan 0001 00:00:00 +0000

Remote MCP servers let you host tool endpoints that Claude connects to over the network, enabling shared infrastructure across teams and persistent service integrations. Pay close attention to the authentication and transport sections — remote servers use SSE or streamable HTTP rather than stdio, which changes how you handle connection lifecycle and error recovery. A frequent gotcha is failing to implement proper OAuth or token refresh flows, causing silent tool failures mid-conversation. This guide pairs well with the MCP Connector docs to compare Anthropic-hosted versus self-hosted approaches to serving tools.

Role-Based Access Control (RBAC)

Mon, 01 Jan 0001 00:00:00 +0000

Control access to crews, tools, and data with roles, scopes, and granular permissions.

Routing Queries to Data Sources

Mon, 01 Jan 0001 00:00:00 +0000

Build an agentic RAG system that routes queries to the most relevant tools based on the query’s nature.

Run prompts on a schedule

Mon, 01 Jan 0001 00:00:00 +0000

Use /loop and the cron scheduling tools to run prompts repeatedly, poll for status, or set one-time reminders within a Claude Code session.

S3 Reader Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘S3ReaderTool’ enables CrewAI agents to read files from Amazon S3 buckets.

S3 Writer Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘S3WriterTool’ enables CrewAI agents to write content to files in Amazon S3 buckets.

Scrape Element From Website Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ScrapeElementFromWebsiteTool’ enables CrewAI agents to extract specific elements from websites using CSS selectors.

Scrape Website

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ScrapeWebsiteTool’ is designed to extract and read the content of a specified website.

Scrapegraph Scrape Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ScrapegraphScrapeTool’ leverages Scrapegraph AI’s SmartScraper API to intelligently extract content from websites.

Scrapfly Scrape Website Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ScrapflyScrapeWebsiteTool’ leverages Scrapfly’s web scraping API to extract content from websites in various formats.

Selenium Scraper

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SeleniumScrapingTool’ is designed to extract and read the content of a specified website using Selenium.

Self-deployment

Mon, 01 Jan 0001 00:00:00 +0000

Deploy Mistral AI models on your infrastructure using vLLM, TensorRT-LLM, TGI, or tools like SkyPilot and Cerebrium

SEP-1577: Sampling With Tools

Mon, 01 Jan 0001 00:00:00 +0000

Sampling With Tools

SEP-1577: Sampling With Tools

Mon, 01 Jan 0001 00:00:00 +0000

Sampling With Tools

SEP-973: Expose additional metadata for Implementations, Resources, Tools and Prompts

Mon, 01 Jan 0001 00:00:00 +0000

Expose additional metadata for Implementations, Resources, Tools and Prompts

SEP-973: Expose additional metadata for Implementations, Resources, Tools and Prompts

Mon, 01 Jan 0001 00:00:00 +0000

Expose additional metadata for Implementations, Resources, Tools and Prompts

SerpApi Google Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SerpApiGoogleSearchTool’ performs Google searches using the SerpApi service.

SerpApi Google Shopping Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SerpApiGoogleShoppingTool’ searches Google Shopping results using SerpApi.

Server Tools

Mon, 01 Jan 0001 00:00:00 +0000

Shell

Mon, 01 Jan 0001 00:00:00 +0000

Run shell commands in hosted containers or your own local runtime.

SingleStore Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SingleStoreSearchTool’ safely executes SELECT/SHOW queries on SingleStore with pooling.

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Upload, manage, and attach reusable skills to hosted environments.

Snowflake Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SnowflakeSearchTool’ enables CrewAI agents to execute SQL queries and perform semantic search on Snowflake data warehouses.

Spark-Pinecone connector

Mon, 01 Jan 0001 00:00:00 +0000

Spider Scraper

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SpiderTool’ is designed to extract and read the content of a specified website using Spider.

Stagehand Tool

Mon, 01 Jan 0001 00:00:00 +0000

Web automation tool that integrates Stagehand with CrewAI for browser interaction and automation

Streaming for tool use (function calling)

Mon, 01 Jan 0001 00:00:00 +0000

Guide on implementing streaming for tool use in Cohere’s platform and details on the events stream (API v2).

Streaming Tools

Mon, 01 Jan 0001 00:00:00 +0000

Strict Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

Tavily Extractor Tool

Mon, 01 Jan 0001 00:00:00 +0000

Extract structured content from web pages using the Tavily API

Tavily Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

Perform comprehensive web searches using the Tavily Search API

Templates

Mon, 01 Jan 0001 00:00:00 +0000

Start faster with curated Agent Builder templates and customize tools, prompts, and triggers.

Templates

Mon, 01 Jan 0001 00:00:00 +0000

Start faster with curated Fleet templates and customize tools, prompts, and channels.

Testset Generation for Agents or Tool use cases

Mon, 01 Jan 0001 00:00:00 +0000

Text Editor Tool

Mon, 01 Jan 0001 00:00:00 +0000

The text editor tool gives Claude the ability to view, create, and edit files through structured operations like insert, replace, and undo, making it central to coding agent implementations. Unlike having Claude output code in a message for you to copy, this tool enables autonomous multi-step file modifications within an agentic loop. Focus on understanding the exact replacement semantics, since the tool requires unique string matches for edits and will fail if the target string appears multiple times. This tool works best when combined with the bash tool for running tests after edits, forming the core edit-verify cycle that coding agents depend on.

Third-Party Tools

Mon, 01 Jan 0001 00:00:00 +0000

Tool Calling

Mon, 01 Jan 0001 00:00:00 +0000

Connect models to external tools and APIs

Tool Combinations

Mon, 01 Jan 0001 00:00:00 +0000

Tool integrations

Mon, 01 Jan 0001 00:00:00 +0000

Give your agents access to a wide range of tools and services.

Tool integrations

Mon, 01 Jan 0001 00:00:00 +0000

Give your agents access to a wide range of tools and services.

Tool limitations

Mon, 01 Jan 0001 00:00:00 +0000

Tool performance

Mon, 01 Jan 0001 00:00:00 +0000

Tool Reference

Mon, 01 Jan 0001 00:00:00 +0000

Tool Repository

Mon, 01 Jan 0001 00:00:00 +0000

Using the Tool Repository to manage your tools

Tool Runner

Mon, 01 Jan 0001 00:00:00 +0000

Tool search

Mon, 01 Jan 0001 00:00:00 +0000

Use tool search to defer large tool surfaces, group related tools with namespaces, and load only the relevant functions at runtime.

Tool Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The tool search tool enables deferred tool loading, allowing agents with large tool catalogs to discover and activate tools on demand rather than loading everything into context upfront. This is critical for agents that integrate many MCP servers or have hundreds of available tools, since stuffing all tool definitions into the system prompt degrades model performance and wastes tokens. Pay attention to the query semantics: keyword search returns ranked matches while direct selection loads a specific tool by name. Architect your agent so that commonly used tools are always loaded and niche tools are deferred behind search to keep context windows lean.

Tool use & agents - Cohere on Azure AI Foundry

Mon, 01 Jan 0001 00:00:00 +0000

A guide for using tool use and building agents with Cohere’s Command models on Azure AI Foundry (API v2).

Tool use & agents - quickstart

Mon, 01 Jan 0001 00:00:00 +0000

A quickstart guide for using tool use and building agents with Cohere’s Command models (v2 API).

Tool Use With Prompt Caching

Mon, 01 Jan 0001 00:00:00 +0000

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Understanding tools and how they enable human-in-the-loop AI workflows

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Tools are the most commonly used MCP primitive – they let the model invoke server-side functions with structured inputs and receive results. Focus on the JSON Schema-based input validation, which is how the model knows what arguments a tool accepts. A critical detail is that tool calls are model-initiated but require human approval in most host implementations, so design your tool descriptions to be clear enough that users understand what they are approving. Keep tool names concise and descriptions precise, as the model relies heavily on them for deciding when and how to call each tool.

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Understanding and leveraging tools within the CrewAI framework for agent collaboration and task execution.

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Tools & Integrations

Mon, 01 Jan 0001 00:00:00 +0000

Connect external apps and manage internal tools your agents can use.

Tools Overview

Mon, 01 Jan 0001 00:00:00 +0000

Discover CrewAI’s extensive library of 40+ tools to supercharge your AI agents

Tools reference

Mon, 01 Jan 0001 00:00:00 +0000

Complete reference for the tools Claude Code can use, including permission requirements.

Toolsets

Mon, 01 Jan 0001 00:00:00 +0000

Tracing and logging evaluations with Observability tools

Mon, 01 Jan 0001 00:00:00 +0000

Troubleshooting Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

TXT RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘TXTSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a text file.

Usage patterns for tool use (function calling)

Mon, 01 Jan 0001 00:00:00 +0000

Guide on implementing various tool use patterns with the Cohere Chat endpoint such as parallel tool calling, multi-step tool use, and more (API v2).

Use the Playground to experiment with prompts

Mon, 01 Jan 0001 00:00:00 +0000

Simplify the process of iterating on LLM prompts and responses

Use tools in a prompt

Mon, 01 Jan 0001 00:00:00 +0000

Use Weave with W&B training runs

Mon, 01 Jan 0001 00:00:00 +0000

Integrate Weave traces with W&B training runs to gain deep visibility into model behavior during training, capturing function execution details and diagnostics alongside traditional ML metrics in customizable workspace dashboards.

Using tools

Mon, 01 Jan 0001 00:00:00 +0000

Extend model capabilities with tools — built-in (web search, file search, code interpreter) and custom (function calling, remote MCP servers).

Vision Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘VisionTool’ is designed to extract text from images.

Weaviate Vector Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘WeaviateVectorSearchTool’ is designed to search a Weaviate vector database for semantically similar documents using hybrid search.

Web Fetch Tool

Mon, 01 Jan 0001 00:00:00 +0000

The web fetch tool is an Anthropic-provided built-in tool that lets Claude retrieve content from URLs during a conversation, converting HTML to markdown for processing. This is a key building block for agents that need to access live web data, documentation, or API responses without requiring you to build custom tool infrastructure. Note that authenticated URLs will fail since the tool operates without session cookies or tokens, so you need alternative approaches for private resources. Compare this with the web search tool, which discovers URLs, whereas web fetch retrieves content from known URLs you or the model already have.

Web search

Mon, 01 Jan 0001 00:00:00 +0000

Built-in web search tool that lets models search the internet for current information before generating responses — grounding outputs in real-time data.

Web Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The web search tool gives Claude the ability to query search engines and incorporate up-to-date information into its responses, directly addressing the knowledge cutoff limitation inherent to all LLMs. This is essential for agents that need to answer questions about current events, recent software releases, or rapidly changing documentation. Be mindful that search results are summaries, not full page content – pair this tool with the web fetch tool when you need to deeply read a specific result. Search queries constructed by the model can sometimes be overly broad, so providing domain filtering constraints improves relevance significantly.

Website RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘WebsiteSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a website.

Workspace setup

Mon, 01 Jan 0001 00:00:00 +0000

Add required workspace secrets for models and tools used by Agent Builder.

Workspace setup

Mon, 01 Jan 0001 00:00:00 +0000

Add required workspace secrets for models and tools used by Fleet.

XML RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘XMLSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a XML file.

YouTube Channel RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘YoutubeChannelSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a Youtube channel.

YouTube Video RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘YoutubeVideoSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a Youtube video.

Zapier Actions Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ZapierActionsAdapter’ exposes Zapier actions as CrewAI tools for automation.