index.md

title	Tools Overview
description	Overview of tool types available in Agent Framework and provider support matrix.
zone_pivot_groups	programming-languages
author	eavanvalkenburg
ms.topic	reference
ms.author	edvan
ms.date	02/09/2026
ms.service	agent-framework

Tools Overview

Agent Framework supports many different types of tools that extend agent capabilities. Tools allow agents to interact with external systems, execute code, search data, and more.

Tool Types

Tool Type	Description
Function Tools	Custom code that agents can call during conversations
Tool Approval	Human-in-the-loop approval for tool invocations
Code Interpreter	Execute code in a sandboxed environment
File Search	Search through uploaded files
Web Search	Search the web for information
Hosted MCP Tools	MCP tools hosted by Microsoft Foundry
Local MCP Tools	MCP tools running locally or on custom servers

:::zone pivot="programming-language-csharp"

Provider Support Matrix

The OpenAI and Azure OpenAI providers each offer multiple client types with different tool capabilities. Azure OpenAI clients mirror their OpenAI equivalents.

Tool Type	Chat Completion	Responses	Assistants	Foundry	Anthropic	Ollama	GitHub Copilot	Copilot Studio
Function Tools	✅	✅	✅	✅	✅	✅	✅	✅
Tool Approval	❌	✅	❌	✅	❌	❌	❌	❌
Code Interpreter	❌	✅	✅	✅	❌	❌	❌	❌
File Search	❌	✅	✅	✅	❌	❌	❌	❌
Web Search	✅	✅	❌	❌	❌	❌	❌	❌
Hosted MCP Tools	❌	✅	❌	✅	✅	❌	❌	❌
Local MCP Tools	✅	✅	✅	✅	✅	✅	✅	❌

Note

The Chat Completion, Responses, and Assistants columns apply to both OpenAI and Azure OpenAI — the Azure variants mirror the same tool support as their OpenAI counterparts.

:::zone-end

:::zone pivot="programming-language-python"

Provider Support Matrix

The OpenAI and Azure OpenAI providers each offer multiple client types with different tool capabilities. Azure OpenAI clients mirror their OpenAI equivalents.

Tool Type	Chat Completion	Responses	Assistants	Foundry	Anthropic	Claude Agent	Ollama	GitHub Copilot
Function Tools	✅	✅	✅	✅	✅	✅	✅	✅
Tool Approval	❌	✅	❌	✅	❌	❌	❌	❌
Code Interpreter	❌	✅	✅	✅	✅	❌	❌	❌
File Search	❌	✅	✅	✅	❌	❌	❌	❌
Web Search	✅	✅	❌	✅	✅	❌	❌	❌
Image Generation	❌	❌	❌	✅	❌	❌	❌	❌
Hosted MCP Tools	❌	✅	❌	✅	✅	❌	❌	❌
Local MCP Tools	✅	✅	✅	✅	✅	✅	✅	✅

Note

The Chat Completion, Responses, and Assistants columns apply to both OpenAI and Azure OpenAI — the Azure variants mirror the same tool support as their OpenAI counterparts. Local MCP Tools work with any provider that supports function tools.

:::zone-end

Using an Agent as a Function Tool

You can use an agent as a function tool for another agent, enabling agent composition and more advanced workflows. The inner agent is converted to a function tool and provided to the outer agent, which can then call it as needed.

:::zone pivot="programming-language-csharp"

Call .AsAIFunction() on an AIAgent to convert it to a function tool that can be provided to another agent:

// Create the inner agent with its own tools
AIAgent weatherAgent = new AIProjectClient(
    new Uri("<your-foundry-project-endpoint>"),
    new DefaultAzureCredential())
     .AsAIAgent(
        model: "gpt-4o-mini",
        instructions: "You answer questions about the weather.",
        name: "WeatherAgent",
        description: "An agent that answers questions about the weather.",
        tools: [AIFunctionFactory.Create(GetWeather)]);

// Create the main agent and provide the inner agent as a function tool
AIAgent agent = new AIProjectClient(
    new Uri("<your-foundry-project-endpoint>"),
    new DefaultAzureCredential())
     .AsAIAgent(
        model: "gpt-4o-mini",
        instructions: "You are a helpful assistant.",
        tools: [weatherAgent.AsAIFunction()]);

// The main agent can now call the weather agent as a tool
Console.WriteLine(await agent.RunAsync("What is the weather like in Amsterdam?"));

Warning

DefaultAzureCredential is convenient for development but requires careful consideration in production. In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid latency issues, unintended credential probing, and potential security risks from fallback mechanisms.

:::zone-end

:::zone pivot="programming-language-python"

Call .as_tool() on an agent to convert it to a function tool that can be provided to another agent:

import os
from agent_framework.openai import OpenAIChatCompletionClient
from azure.identity import AzureCliCredential

# Create the inner agent with its own tools
weather_agent = OpenAIChatCompletionClient(
    model=os.environ["AZURE_OPENAI_CHAT_COMPLETION_MODEL"],
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
    credential=AzureCliCredential(),
).as_agent(
    name="WeatherAgent",
    description="An agent that answers questions about the weather.",
    instructions="You answer questions about the weather.",
    tools=get_weather
)

# Create the main agent and provide the inner agent as a function tool
main_agent = OpenAIChatCompletionClient(
    model=os.environ["AZURE_OPENAI_CHAT_COMPLETION_MODEL"],
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
    credential=AzureCliCredential(),
).as_agent(
    instructions="You are a helpful assistant.",
    tools=weather_agent.as_tool()
)

# The main agent can now call the weather agent as a tool
result = await main_agent.run("What is the weather like in Amsterdam?")
print(result.text)

You can also customize the tool name, description, and argument name:

weather_tool = weather_agent.as_tool(
    name="WeatherLookup",
    description="Look up weather information for any location",
    arg_name="query",
    arg_description="The weather query or location"
)

:::zone-end

Next steps

[!div class="nextstepaction"] Function Tools