As agentic workflows scale, orchestration can become a bottleneck. Today, we’re simplifying this by allowing developers to combine built-in tools (such as Google Search and Google Maps) with custom functions in a single request, circulate context across tool calls and turns for more complex reasoning and extend Grounding with Google Maps to the Gemini 3 model family.
New tooling capabilities in the API
Combine built-in and custom tools in the same interaction
Previously, developers had to carefully orchestrate when to use built-in tools (like Google Search) versus when to rely on a custom function declaration. Now, you can pass both built-in tools and your own custom tools in the same request. This allows Gemini to easily pivot between fetching public data via Google Search then calling your backend without separate orchestration steps, reducing end-to-end latency and simplifying agent architectures.
This has been a top request from developers since we introduced built-in tools and we are excited to see how you combine file search, Google Maps, Search, and custom functions together!
Cross-tool context circulation for built-in tools
In multi-step workflows, models often need to use the output of one tool as the input for another. Context circulation for built-in tools preserves every tool call and its response in the model’s context, so follow-up steps can access and reason over that data. For example, Gemini can now use a built-in tool to get real-time weather data and circulate that context to a custom tool that books a venue.
Tool response IDs
To improve debuggability and ensure precise mapping during asynchronous tool executions, we’ve introduced unique call identifiers (`id`) for every tool call. These IDs allow developers to identify specific tool calls requested by the model with the exact client responses, which is especially critical when handling parallel function calling and cross-tool context.
Here’s a code snippet showing an example of a multi-tool combination flow with Grounding with Google Search.
