Open Brain
Back
GoogleOfficial ReleaseOfficial SourcecontextNew

Introducing Tool Retrieval in the Gemini API

Defer long-tail tool schemas while keeping frequent tools loaded, then measure token savings because retrieved schemas remain billable.

GoogleNov 19, 20262 min
Open SourceOpen MarkdownOpen JSON
Source Summary

Gemini Tool Retrieval defers full tool schemas until an agent needs them, keeping large tool libraries out of most requests. Measure token use on your traffic, since loaded schemas remain billable in the conversation.

Practical Implication

For agents with large tool libraries, leave frequent tools loaded and defer the long tail with `tool_search` and `defer_loading: true`. Remote MCP tools can also be loaded on demand, and deferred schemas keep the prompt prefix stable for caching.

Agent-Ready Context
**Tool Retrieval** is in preview in the Gemini Interactions API. Deferred tools keep their names and descriptions visible, while their parameter schemas load only after the model requests a specific tool; the search and call happen in one API request.

For agents with large tool libraries, leave frequent tools loaded and defer the long tail with `tool_search` and `defer_loading: true`. Remote MCP tools can also be loaded on demand, and deferred schemas keep the prompt prefix stable for caching.

There is no separate feature charge, but search adds a small fixed input-token block and loaded schemas are billed as input for the rest of the conversation. Savings depend on how many schemas remain unused, so measure against your own traffic.
Context Map
contextcoding#tool-use#context-engineering#context-cachingGeneric AgentPrepare Coding Session
Rate This Item
Personal Note

No note yet. Notes are included in exported bundles.

Related — Every Edge Explained

No approved edges yet for this post.