Original sourceGoogle
Summary
Google previewed tool search in the Gemini API's Interactions API, letting agents avoid loading all tool schemas at once. After developers add the tool_search tool and set defer_loading for specified tools, the model first sees only tool names and descriptions, with actual schemas loaded within the…
Key points
- Directly addresses token cost, latency and accuracy drift caused by tool count inflation.
- Tool scale is a practical bottleneck for agent deployment; on-demand loading lets long-tail tools be included too.
- Agent developers should measure the impact of deferred loading on latency and accuracy before deciding which frequently used tools stay preloaded.
Editorial note
This page is Code & Chain's editorial summary of public sources. It may be prepared with AI assistance and published through an automated workflow. Refer to the original sources; this content is not investment, legal, or tax advice.