AI glossary
Function calling (tool use)
A model capability to request that an app run a specific function with specific arguments, such as “search_flights(from, to, date)”.
The developer describes the available tools — name, purpose and the parameters they accept. When the model decides a tool would help, it replies with a structured request instead of text. The app runs the function and sends the result back, and the model continues.
The model never runs code itself; your application decides what actually happens. Function calling is the building block of agents, and MCP is a standard way to offer tools to many apps at once.
Example: You define a tool get_order(number). A customer asks “where is my order 4821?”. The model replies with a call to get_order with the number 4821, your app queries the database and the model writes the answer with the real status.
In practice
- Describe each tool as you would to a new colleague: what it does, when to use it and what each parameter means.
- Always validate the arguments before running anything.
- Ask the user to confirm actions that change data or spend money.
How tools are shared across apps: what MCP is.
