Intermediate7 min

Tool Execution Loop

When a model returns tool calls, execute them and pass results back as ToolMessages. This three-step cycle — invoke → execute → invoke again — is the foundation of every tool-using agent.

Quick Reference

→model.bind_tools([fn]) binds tools to the model for the entire session
→ai_msg.tool_calls is a list of {'name', 'args', 'id'} dicts
→tool.invoke(tool_call) executes the tool and returns a ToolMessage
→tool_choice='any' forces the model to call at least one tool
→tool_choice={'name': 'fn_name'} forces a specific tool

The Execution Cycle

Tool calling follows a three-step cycle: the model generates a tool call, you execute it, then you pass the result back so the model can synthesize a final answer. The model can call multiple tools across multiple turns before producing a final response — you keep looping until ai_msg.tool_calls is empty.

Complete tool call cycle

Forcing Tool Calls

By default the model decides whether to call a tool based on context. Use tool_choice to force the model to always call a tool, or to call a specific one.

Parallel Tool Calls

Models can call multiple tools in a single response when the tasks are independent. The ai_msg.tool_calls list will contain multiple entries — execute them all before invoking the model again.

Sign in to read this article

This is a premium article. Sign in with your Google account to continue.