Tool calling
A model emits a structured request to invoke an external function, and the result is returned as context for its next step.
Tool calling is the mechanism that gives a language model effects beyond generating text. The model does not execute the tool - the host runtime does - but the model decides which tool, with what arguments, and how to interpret the result. The security surface is the set of tools exposed and their permissions.
Explained in depth
How a model asks for a function to be run, why the model never runs it, and where the boundary between a fluent request and an executed action actually sits.
Agent planningWhy interleaving reasoning with action outperforms planning everything up front, what ReAct and Reflexion actually showed, and where a plan should be allowed to change.
Implemented by
- Model Context Protocol
- OpenAI Agents SDK
- LangGraph