Tool reference

This page is a reference for the tools Anthropic provides and the optional properties you can set on any tool definition. For a conceptual introduction to tool use, see Tool use with Claude. For guidance on implementing tool use in your application, see Define tools.

Anthropic-provided tools

Anthropic provides two kinds of tools: server tools that execute on Anthropic's infrastructure, and client tools where Anthropic defines the schema but your application handles execution. Both kinds appear in your request's tools array alongside any user-defined tools.

For model compatibility, see each tool's page. Supported models vary by tool and by tool version.

Tool versioning

Most Anthropic-provided tools carry a _YYYYMMDD suffix in the type string. A new version is released when the tool's behavior, schema, or model support changes. Older versions remain available so that existing integrations continue to work.

When a tool has multiple active versions, the relationship between them varies:

• Capability-keyed: web_search_20260209 and web_fetch_20260209 add dynamic content filtering over their predecessors. code_execution_20260120 adds programmatic tool calling from within the sandbox. In each case, both the new and old versions are current; which one you use depends on whether you need the new capability.
• Model-keyed: text_editor_20250728 is for Claude 4 models and text_editor_20250124 is for earlier models. The version you use depends on the model you target.
• Variant, not version: tool_search_tool_regex_20251119 and tool_search_tool_bm25_20251119 are two search algorithms released together. Neither supersedes the other.
• Legacy: code_execution_20250522 supports only Python. code_execution_20250825 adds Bash and file operations.

The mcp_toolset type is not date-versioned; versioning is carried in the anthropic-beta header instead.

Tool definition properties

Every tool in the tools array, including user-defined tools, accepts optional properties that control how the tool is loaded, who can call it, and how its inputs are validated. These properties compose: you can set defer_loading and cache_control and strict on the same tool.

allowed_callers values

allowed_callers is an array that accepts any combination of:

Omitting "direct" from the array (for example, "allowed_callers": ["code_execution_20260120"]) means the tool is callable only from within code execution. The response's tool_use block includes a caller field that identifies which caller called the tool. See Programmatic tool calling for the full treatment, including the caller response shape and error behavior.

defer_loading and prompt caching

Tools with defer_loading: true are stripped from the rendered tools section before the cache key is computed. They don't appear in the system-prompt prefix at all. When tool search discovers a deferred tool and returns a tool_reference for it, the tool's full definition is expanded inline at that point in the conversation body, not in the prefix.

This means defer_loading: true preserves your prompt cache. You can add deferred tools to a request without invalidating an existing cache entry, and the cache remains valid across the turn where the tool is discovered and the turn where it's called.

For how to combine defer_loading with cache_control breakpoints, see the Tool search tool prompt caching guidance.