Definition: Function calling, also called tool use, is a capability that lets a language model choose a predefined function and return structured arguments for it, so an application can run that function and pass the result back.
Developers describe each available tool with a name, a purpose and a parameter schema. When a request arrives, the model decides whether a tool is needed and replies with the tool name and arguments in a structured format. The application, not the model, executes the call, checks the result and returns it to the model for the next step.
Function calling is how a model reaches live data and takes actions: looking up an order, querying a database or creating a ticket. It is the foundation of AI agents, and standards such as the Model Context Protocol make tools reusable across applications.
Good tool design keeps each function narrow, validates every argument, enforces the caller's permissions in code and logs each call. Teams test tool selection with evaluation cases, because picking the wrong tool or inventing an argument is a common failure.
Ryz AI agent developers and API developers build tool integrations for LLM applications, working on your team.
Thanks — your message has been sent. We’ll get back to you soon.
Something went wrong while sending your message. Please try again or email info@ryzlabs.com.