Gemini API adds one-call tool chaining and Maps grounding for Gemini 3

The core change is that Gemini can now orchestrate built-in tools and developer-defined functions in one request. In Google's launch thread, the example combines Google Search with a custom check_inventory function, and the model returns a sequence including search calls, results, a "thought," and multiple function calls. The same post says this is available natively in the Interactions API and as an opt-in path through generate_content, with more detail in the Interactions docs and the tool-combination docs.

The other important implementation detail is context handling. Google's follow-up thread says built-in tools now work with function calling and that the platform "do[es] context circulation with built-in tools for better model performance." A supporting practitioner summary in this post adds that every tool call now has an ID, which matters for tracing multi-step chains and asynchronous workflows.

Maps is the newly expanded built-in tool. Google's announcement says Google Maps is now available for Gemini 3 models, and the product thread explicitly describes this as "Grounding with Google Maps" for Gemini 3. That widens the set of built-in tools developers can mix into one-call agent flows beyond Search, File Search, and URL Context.

Testing is already visible in the product surface. The AI Studio screenshot shows a "Grounding with Google Maps" toggle in Playground with Gemini 3.1 Pro Preview selected, which makes this easier to prototype before wiring the same behavior into application code. A smaller developer post in this note underscores the practical use case: teams that had been trying to couple Search or Maps grounding with custom functions can now do that directly instead of stitching separate steps together.