This page covers the tool-call lifecycle: reading tool_use blocks from Claude's response, formatting tool_result blocks in your reply, and signaling errors. For the SDK abstraction that handles this automatically, see Tool Runner.

Claude's response differs based on whether it uses a client or server tool.

Handling results from client tools

The response will have a stop_reason of tool_use and one or more tool_use content blocks that include:

id: A unique identifier for this particular tool use block. This will be used to match up the tool results later.
name: The name of the tool being used.
input: An object containing the input being passed to the tool, conforming to the tool's input_schema.

A tool_use block for a member of the computer use or browser use toolset also carries a toolset_name field ("computer" or "browser"). Its name is the member tool Claude is calling, such as screenshot or navigate, so dispatch those blocks on both fields.

When you receive a tool use response for a client tool, you should:

Extract the name, id, and input from the tool_use block.
Run the actual tool in your codebase corresponding to that tool name, passing in the tool input.
Continue the conversation by sending a new message with the role of user, and a content block containing the tool_result type and the following information:
- tool_use_id: The id of the tool use request this is a result for.
- content (optional): The result of the tool, as a string (for example, "content": "15 degrees"), a list of nested content blocks (for example, "content": [{"type": "text", "text": "15 degrees"}]), or a list of document blocks (for example, "content": [{"type": "document", "source": {"type": "text", "media_type": "text/plain", "data": "15 degrees"}}]). These content blocks can use the text, image, document, or search_result types.
- is_error (optional): Set to true if the tool execution resulted in an error.

A tool_result that answers a computer use or browser use member block must also echo the same toolset_name value as the tool_use block; a member result that omits it is rejected. Its content is also narrower: a member result may contain only text and image blocks, and a browser use result may add one browser_state block (the tab-management members return only that block).

Tool result blocks must immediately follow their corresponding tool use blocks in the message history. You cannot include any messages between the assistant's tool use message and the user's tool result message.
In the user message containing tool results, the tool_result blocks must come FIRST in the content array. Any text must come AFTER all tool results.
If the assistant turn also called a server tool that has no result block yet, the user message must contain only tool_result blocks. Text after the results ends the turn early; for a server tool Claude called directly, the request then fails with a 400 error that names the unresolved server tool. See Stop reasons and fallback.

For example, this will cause a 400 error:

{
  "role": "user",
  "content": [
    { "type": "text", "text": "Here are the results:" }, // ❌ Text before tool_result
    { "type": "tool_result", "tool_use_id": "toolu_01" /* ... */ }
  ]
}

This is correct when the assistant turn calls only client tools:

{
  "role": "user",
  "content": [
    { "type": "tool_result", "tool_use_id": "toolu_01" /* ... */ },
    { "type": "text", "text": "What should I do next?" } // ✅ Text after tool_result
  ]
}

If you receive an error like "tool_use ids were found without tool_result blocks immediately after", check that your tool results are formatted correctly.

After receiving the tool result, Claude will use that information to continue generating a response to the original user prompt.

Handling results from server tools

Claude executes the tool internally and incorporates the results directly into its response without requiring additional user interaction.

Unlike APIs that separate tool use or use special roles like tool or function, the Claude API integrates tools directly into the user and assistant message structure.

Messages contain arrays of text, image, tool_use, and tool_result blocks. user messages include client content and tool_result, while assistant messages contain AI-generated content and tool_use.

Handling errors with is_error

There are a few different types of errors that can occur when using tools with Claude:

```json JSON
{
  "role": "user",
  "content": [
    {
      "type": "tool_result",
      "tool_use_id": "toolu_01A09q90qw90lq917835lq9",
      "content": "ConnectionError: the weather service API is not available (HTTP 500)",
      "is_error": true
    }
  ]
}
```

Claude will then incorporate this error into its response to the user. For example: "I'm sorry, I was unable to retrieve the current weather because the weather service API is not available. Please try again later."

<Tip>
  Write instructive error messages. Instead of generic errors like `"failed"`, include what went wrong and what Claude should try next (for example, `"Rate limit exceeded. Retry after 60 seconds."`). This gives Claude the context it needs to recover or adapt without guessing.
</Tip>

However, you can also continue the conversation forward with a `tool_result` that indicates the error, and Claude will try to use the tool again with the missing information filled in:

```json JSON
{
  "role": "user",
  "content": [
    {
      "type": "tool_result",
      "tool_use_id": "toolu_01A09q90qw90lq917835lq9",
      "content": "Error: Missing required 'location' parameter",
      "is_error": true
    }
  ]
}
```

If a tool request is invalid or missing parameters, Claude will retry 2-3 times with corrections before apologizing to the user.

<Tip>
  To eliminate invalid tool calls entirely, use [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) with `strict: true` on your tool definitions. This guarantees that tool inputs will always match your schema exactly, preventing missing parameters and type mismatches.
</Tip>

For web search specifically, possible error codes include:

* `too_many_requests`: Rate limit exceeded
* `invalid_input`: Invalid search query parameter
* `max_uses_exceeded`: Maximum web search tool uses exceeded
* `query_too_long`: Query exceeds maximum length
* `unavailable`: An internal error occurred

Handle tool calls

Handling results from client tools

Handling results from server tools

Handling errors with is_error

Next steps