Tool calling is the mechanism that lets a language model request an external action instead of only generating text: given a set of defined functions, the model emits a structured request naming one and its arguments, the caller executes it, and the result feeds back into the conversation.
How does tool calling actually work?
The caller describes each available tool as a name, a short description, and a schema for its arguments. When an external action would help, the model does not run anything itself: it emits a structured request naming the tool and its arguments, then stops. The application executes the real call and sends the result back for the model’s next step.
Tool calling vs function calling: is there a difference?
Not really, which is why one canonical page covers both rather than splitting them: function calling was the original name, coined when the capability meant calling one of a small set of predefined functions. Tool calling is now the more common term as the mechanism grew to cover broader categories like web search and computer use, which are still “tools” but are not literally functions in a codebase.
Where does tool calling fit inside an AI agent?
Tool calling is the mechanism an AI agent repeats on every step of its loop, and it is the foundation MCP standardizes: instead of every application describing its tools in its own format, MCP gives a client one shared way to discover and call them. Without reliable tool calling, agentic AI does not exist as a category.
Frequently asked questions
Is tool calling the same as function calling?
Yes, they describe the same mechanism. Function calling is the older, narrower term from when a model could only request predefined functions. Tool calling is the more current term as the same mechanism expanded to cover web search, code execution, and computer use, not only custom functions.
Does the model actually run the tool itself?
No. The model only decides which tool to call and with what arguments, and returns that as structured output. Your application, or an MCP server, is the part that actually executes the call and sends the real result back to the model.
Is tool calling enough to build an AI agent?
It is the mechanism an agent runs on, but not the whole thing. An agent also needs a loop that decides when to keep going, retry, or stop, and usually a way to standardize which tools are available, which is the problem MCP solves.