Gemini API previews Tool Retrieval: tool parameter schemas load on demand instead of sending the whole tool library on every request
With dozens of tools, sending every schema on every request costs tokens and lowers tool-selection accuracy. How Gemini's server-side fix is switched on and billed, for agent teams with dozens of tools or more.
// Key points
- It is in preview in the Interactions API: add a tool_search tool to the request and set defer_loading to true on the tools to hold back.
- The model still sees every deferred tool's name and description, asks for one by name, and the API loads the full schema and runs the function call in the same request; the search runs server-side with no index to build.
- Deferred schemas stay out of the start of the prompt and loaded ones are appended later, so the cached prefix stays the same turn to turn; it also works with remote MCP servers, loading a whole server's tools on demand.
- No separate charge: turning it on adds a small fixed block of input tokens, and each loaded schema is billed as input for the rest of the conversation; a client-side retrieval mode adds one round trip per search.
Builder's takeThis is the first time on-demand tool loading has become a standard switch in a major API, so an agent can carry hundreds of tools without paying full price for them. My advice: keep the three to five most-used tools loaded, defer the long tail, then compare input tokens and wrong-tool picks on your own traffic before and after. A backend like PandaClaws, wired to many publishing channels, is exactly where the long tail lives.
// Background · from #Google
Full timeline →- Nov 20 The Gemini app for Mac gets computer use: it completes multi-step tasks across local files, desktop apps and the web in an isolated background window, with key actions needing your approval
- Nov 20 The Genie 4 world model comes to the Gemini API: interactive 720p worlds at 24 fps with synchronized native audio, from a text prompt or reference image
- Nov 19 Google releases Gemini 4 Neon at $3 input and $15 output per million tokens, with 32% lower cost per task than Carbon at its default high level