Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

how-tool-use-works changedagents-and-tools/tool-use/how-tool-use-works

Nearest release: v2.1.238, published an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+6added
Lines−6removed
From line 24 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits3to this page, all time

The whole hunk

from line 24, old and new numbered
/
lines
from line 24
2424 
2525### Anthropic-schema tools (client-executed)
2626 
27For a handful of common operations (managing scratchpad memory, running shell commands, editing files, controlling a browser), Anthropic publishes the tool schema and your application handles execution. The tools in this category are [`memory`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool), [`bash`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [`text_editor`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool), and [`computer`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool).
27For a handful of common operations (managing scratchpad memory, running shell commands, editing files, controlling a desktop or a browser), Anthropic publishes the tool schema and your application handles execution. The tools in this category are [`memory`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool), [`bash`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [`text_editor`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool), [`computer`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), and [`browser`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool).
2828 
2929The execution model is identical to user-defined tools: the response contains a `tool_use` block, your code runs the operation, and you send back a `tool_result`. The reason to use an Anthropic-schema tool instead of defining your own equivalent is that these schemas are trained-in. Claude has been optimized on thousands of successful trajectories that use these exact tool signatures, so it calls them more reliably and recovers from errors more gracefully than it would with a custom tool that does the same thing. The schema is the interface the model already expects.
3030 
from line 77
7777 
7878## Choosing between approaches
7979 
80| Approach | When to use it | What to expect | Learn more |
81| ----------------------------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- |
82| User-defined client tools | Custom business logic, internal APIs, proprietary data | You handle execution and the agentic loop | [Define tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools) |
83| Anthropic-schema client tools | Standard dev operations (bash, file editing, browser control) | You handle execution; Claude calls the tool reliably because the schema is trained-in | [Tool reference](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference) |
84| Server-executed tools | Web search, code sandbox, web fetch | Anthropic handles execution; you read the results instead of producing them | [Server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools) |
80| Approach | When to use it | What to expect | Learn more |
81| ----------------------------- | ------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- |
82| User-defined client tools | Custom business logic, internal APIs, proprietary data | You handle execution and the agentic loop | [Define tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools) |
83| Anthropic-schema client tools | Standard dev operations (bash, file editing, desktop and browser control) | You handle execution; Claude calls the tool reliably because the schema is trained-in | [Tool reference](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference) |
84| Server-executed tools | Web search, code sandbox, web fetch | Anthropic handles execution; you read the results instead of producing them | [Server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools) |
8585 
8686## Next steps
8787 
Feedback