Tool calling, also called function calling, is how a language model asks your program to do something it cannot do by generating text: query a database, call an API, run a calculation. You describe each tool with a name, a description and a JSON schema for its arguments. The model replies with a structured call, your code runs it and returns the result, and the model continues.
The hard parts are in the details: writing descriptions the model understands, validating arguments before anything runs, keeping the tool list short enough that the model picks the right one, and streaming or tracing calls so you can see what happened. These guides cover tool calling from a first agent to planning multi-step calls, approving risky ones and connecting tools over MCP.
The library lists all guides with filters for topic, level, category and reading time.