Gemini API Now Lets Developers Mix Built-In and Custom Tools Together

Google

Mar 20, 2026 · Updated Apr 25, 2026

The Gemini API now lets developers combine Google's built-in tools like Search and Maps with custom functions in a single API call — no separate orchestration needed. Context circulation and unique response IDs for parallel calls ship alongside.

The Gemini API now supports combining built-in tools (Google Search, Google Maps) with custom function declarations in a single request — previously developers had to choose one or the other. Three capabilities ship: combined tool support, cross-tool context circulation that preserves each tool's output so follow-up steps can reason over it, and unique tool response IDs (id) for precise mapping in parallel executions. Grounding with Google Maps also expands to the Gemini 3 model family for spatial data, local business info, and commute times.

This removes the orchestration layer agentic workflows needed when hitting multiple sources — public web via Search, private backend via a custom function. Gemini routes between them, cutting latency and simplifying architectures.

Pass built-in tools and custom functions together in one request to build agents that pivot between public data and internal APIs mid-task — use tool response IDs to trace which call produced which output.

View the full update on blog.google

Google AI Developers

@googleaidevsMar 18

Announcing Gemini API tooling updates 🔧 Developers can now combine built-in tools and custom function calling in a single API call for seamless agentic workflows. New tooling capabilities allow devs to: - Combine built-in and custom tools in the same interaction - Cross-tool context circulation for built-in tools - Tool response IDs We’ve also expanded built-in tooling support to include Grounding with Google Maps for the Gemini 3 family of models, enabling models to access up-to-date spatial data, local business info, and more for accurate location-aware responses. Check out the blog to learn more: https://t.co/dB0sg8ye0O

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from Google →

Keep reading

Google Adds Webhooks to Gemini API to Eliminate Polling Traffic

Google introduced event-driven Webhooks for the Gemini API to replace inefficient polling workflows for long-running tasks and batch processing. This shift simplifies orchestration logic and reduces API traffic for developers building complex agentic applications.

Google Rebuilds Gemini Interactions API to Power Multi-Step Agentic Workflows

Google AI StudioMay 8

Google Rebuilds Gemini Interactions API to Power Multi-Step Agentic Workflows

Google is restructuring the Gemini Interactions API to replace role-based outputs with a structured timeline of execution steps. This shift allows developers to track internal reasoning and tool calls as discrete actions, moving the platform from simple chat to native agentic orchestration.

GeminiMay 12

Google Gemini Uses Personal Intelligence to Build Custom Travel Itineraries

Google expanded Gemini's Personal Intelligence so it can build custom travel itineraries by connecting the dots across a user's Gmail, Google Photos, Search, and YouTube history. Users ask Gemini to combine their dream destinations, favorite activities, and past reservations into a personalized travel plan. Connected apps and personalization settings remain user-controlled.

Vercel Integrates Gemini 3.5 Flash for Parallel Agentic Workflows

VercelMay 19

Vercel Integrates Gemini 3.5 Flash for Parallel Agentic Workflows

Vercel added Google's Gemini 3.5 Flash to its AI Gateway, enabling developers to deploy the new reasoning model with no price markup or additional provider accounts. The integration prioritizes agentic performance, replacing traditional sampling parameters with simplified thinking levels to optimize multi-turn reasoning.