product updateGoogle DeepMind

Google Deepmind adds multi-tool chaining and context circulation to Gemini API

TL;DR

Google Deepmind has expanded the Gemini API to enable multi-tool chaining, allowing developers to combine built-in tools like Google Search and Google Maps with custom functions in a single request. Results from one tool now automatically pass to the next through context circulation, eliminating the need for separate sequential handling.

2 min read
0

Google Deepmind Upgrades Gemini API with Multi-Tool Chaining and Context Circulation

Google Deepmind has expanded the Gemini API with several developer-focused features designed to simplify complex workflows. The core upgrade enables multi-tool chaining, allowing built-in tools like Google Search and Google Maps to be combined with custom functions in a single API request.

What Changed

Previously, developers working with multiple tools had to orchestrate each step separately, requiring sequential API calls and manual result handling between steps. The new system automates this process through context circulation—results from one tool are automatically passed as input to the next tool in the chain.

Google has also introduced unique IDs for each tool call, improving debugging and error tracking capabilities. This makes it easier for developers to trace execution paths and identify which specific tool invocations caused issues in complex workflows.

Google Maps Integration

Google Maps is now available as a data source for the Gemini 3 model family. The integration provides access to location data, business information, and commute times, expanding the types of real-world information Gemini can incorporate into responses.

Implementation Path

Google recommends using the new Interactions API for building these multi-tool workflows. The company has not disclosed specific pricing changes or availability windows for these features.

What This Means

This update addresses a legitimate friction point for developers building agent-based applications. Multi-tool chaining with automatic context passing reduces boilerplate code and latency compared to sequential API calls. However, the practical impact depends on how broadly these tools are available (whether custom tools can truly integrate seamlessly with Google's built-in tools) and pricing implications for tool calls. The addition of Maps data to Gemini 3 is incremental—most competing models already support location-aware responses through various mechanisms. Developers using Gemini will likely find this useful for reducing implementation complexity, but this is a refinement rather than a fundamental capability shift.

Related Articles

product update

Doubao Work launches workbenches with preset skills and tools for 21 professional scenarios

ByteDance's Doubao Work launched a workbench feature on November 16 that bundles preconfigured skills and tools for 21 professional scenarios. It is available in the Doubao Work desktop client and the Doubao desktop app. Users can also build, save and share their own workspaces.

product update

Alibaba's QwenWork Adds Kimi, GLM, DeepSeek, MiniMax and Step Models, With Admin-Level Access Controls

Alibaba's QwenWork office agent opened a broader model menu on November 16, adding third-party models from Kimi, GLM, DeepSeek, MiniMax and Step next to its own Qwen models. Enterprise administrators can set model access by department, user group or individual member.

product update

Google Adds Shareable Interactive Sites to Gemini Notebook, Rolling Out Globally on Web

Google announced on November 16, 2026 that Gemini Notebook can turn a notebook's sources into interactive sites. Outputs now include custom visual explainers, dashboards and project trackers, and the feature is rolling out globally on the web.

product update

Perplexity launches Monitor API: web monitoring priced at $1 per 1,000 successful runs

Perplexity launched the Monitor API on November 16, 2026. It gives developers scheduled topic searches and webpage-change tracking, with filtered updates delivered through the API or signed webhooks. Web monitoring costs $1 per 1,000 successful runs.

Comments

Loading...