Tool use with Claude

Connect Claude to external tools and APIs. Learn where tools execute and how the agentic loop works.

Tool use lets Claude call functions you define or that Anthropic provides. Claude decides when to call a tool based on the user's request and the tool's description, then returns a structured call that your application executes (client tools) or that Anthropic executes (server tools).

Here's the simplest example using a server tool, where Anthropic handles execution:

curl https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-opus-4-7",
    "max_tokens": 1024,
    "tools": [{"type": "web_search_20260209", "name": "web_search"}],
    "messages": [{"role": "user", "content": "What'\''s the latest on the Mars rover?"}]
  }'

ant messages create --transform content --format yaml \
  --model claude-opus-4-7 \
  --max-tokens 1024 \
  --tool '{type: web_search_20260209, name: web_search}' \
  --message '{role: user, content: "What is the latest on the Mars rover?"}'

import anthropic

client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=1024,
    tools=[{"type": "web_search_20260209", "name": "web_search"}],
    messages=[{"role": "user", "content": "What's the latest on the Mars rover?"}],
)
print(response.content)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic();
const response = await client.messages.create({
  model: "claude-opus-4-7",
  max_tokens: 1024,
  tools: [{ type: "web_search_20260209", name: "web_search" }],
  messages: [{ role: "user", content: "What's the latest on the Mars rover?" }]
});
console.log(response.content);

How tool use works

Tools differ primarily by where the code executes. Client tools (including user-defined tools and Anthropic-schema tools like bash and text_editor) run in your application: Claude responds with stop_reason: "tool_use" and one or more tool_use blocks, your code executes the operation, and you send back a tool_result. Server tools (web_search, code_execution, web_fetch, tool_search) run on Anthropic's infrastructure: you see the results directly without handling execution.

For the full conceptual model including the agentic loop and when to choose each approach, see How tool use works.

For connecting to MCP servers, see the MCP connector. For building your own MCP client, see modelcontextprotocol.io.

Tool access is one of the highest-leverage primitives you can give an agent. On benchmarks like LAB-Bench FigQA (scientific figure interpretation) and SWE-bench (real-world software engineering), adding even basic tools produces outsized capability gains, often surpassing human expert baselines.

Tool use examples

For a complete hands-on walkthrough, see the tutorial. For reference examples of individual concepts, see Define tools and Handle tool calls.

What happens when Claude needs more information

If the user's prompt doesn't include enough information to fill all the required parameters for a tool, Claude Opus is much more likely to recognize that a parameter is missing and ask for it. Claude Sonnet may ask, especially when prompted to think before outputting a tool request. But it may also do its best to infer a reasonable value.

For example, given a get_weather tool that requires a location parameter, if you ask Claude "What's the weather?" without specifying a location, Claude (particularly Claude Sonnet) may make a guess about tool inputs:

{
  "type": "tool_use",
  "id": "toolu_01A09q90qw90lq917835lq9",
  "name": "get_weather",
  "input": { "location": "New York, NY", "unit": "fahrenheit" }
}

This behavior is not guaranteed, especially for more ambiguous prompts and for less intelligent models. If Claude Opus doesn't have enough context to fill in the required parameters, it is far more likely to respond with a clarifying question instead of making a tool call.

Pricing

Tool use requests are priced based on:

1. The total number of input tokens sent to the model (including in the tools parameter)
2. The number of output tokens generated
3. For server-side tools, additional usage-based pricing (e.g., web search charges per search performed)

Client-side tools are priced the same as any other Claude API request, while server-side tools may incur additional charges based on their specific usage.

The additional tokens from tool use come from:

• The tools parameter in API requests (tool names, descriptions, and schemas)
• tool_use content blocks in API requests and responses
• tool_result content blocks in API requests

When you use tools, the API also automatically includes a special system prompt for the model which enables tool use. The number of tool use tokens required for each model are listed below (excluding the additional tokens listed above). Note that the table assumes at least 1 tool is provided. If no tools are provided, then a tool choice of none uses 0 additional system prompt tokens.

These token counts are added to your normal input and output tokens to calculate the total cost of a request.

Refer to the models overview table for current per-model prices.

When you send a tool use prompt, just like any other API request, the response will output both input and output token counts as part of the reported usage metrics.

Next steps

Choose your path