Combine Built-in Tools and Function Calling in the Gemini Interactions API

2026-03-24 · Source: philschmid.de - RSS feed · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

The Gemini Interactions API now supports combining built-in tools with custom function declarations within a single request, allowing the Gemini model to autonomously decide tool call order and circulate context. This new capability, released on March 24, 2026, streamlines agent development by removing the need for manual orchestration of tool handoffs. An example demonstrates combining Google Search, URL Context, and a custom `file_incident` function to automatically search for a critical CVE, read its advisory, and file an incident with details like `CVE-2025-55182` and `Critical` severity. Additionally, the API introduces cross-turn context circulation, enabling follow-up questions to reason over previous tool results without re-execution, while still allowing new tool calls for fresh data.

Key takeaway

For AI Engineers building sophisticated agents, the Gemini Interactions API's new tool combination feature simplifies complex workflows. You can now declare multiple tools, both built-in and custom, in one request, letting Gemini manage the execution order and context flow. This reduces boilerplate code and allows your agents to handle multi-step tasks like vulnerability research and incident filing more autonomously, accelerating development and deployment of robust AI applications.

Key insights

Gemini API now combines built-in and custom tools, automating orchestration and context circulation for complex agent workflows.

Principles

• Automate tool orchestration
• Circulate context between tools

Method

Define custom functions and pass them alongside built-in tools (e.g., `google_search`, `url_context`) in a single `client.interactions.create` request. For cross-turn context, pass `previous_interaction_id`.

In practice

• Combine Search, URL Context, and custom functions
• File security incidents automatically
• Maintain context across conversational turns

Topics

• Gemini API
• Function Calling
• Tool Orchestration
• Context Circulation
• AI Agents

Best for: AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• Gemini Interactions API Quick Start — The Gemini Interactions API unifies agentic application development with server-side state, tool orchestration, and multimodal capabilities.
• This Gemini Feature is Wild 🤯 — Gemini's new feature allows users to automate multi-step tasks into repeatable workflows.
• How Gemini Managed Agents Works under the Hood — Gemini Managed Agents abstract complex multi-step AI tasks into a single API call, orchestrating an isolated execution environment.
• Build an AI Research Agent with Google Interactions API & Gemini 3 — Google's Interactions API enables stateful, multi-phase AI agents by managing server-side context and background execution.
• Unleash Your Development Superpowers: Refining the Core Coding Experience — Gemini Code Assist enhances developer productivity through AI-powered automation, collaboration, and customization features.
• Here's What You Should Know About AI Agent Scopes And Tool Lifecycles — The agent.tool() API unifies operational controls for AI agent calls, simplifying development and enhancing reliability.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by philschmid.de - RSS feed.