Tool Calling (Function Calling)
In one sentence
As an LLM generates a response, it calls external tools as needed—such as search, calculations, database queries, or messaging—and continues working based on the results.
The model itself only generates text. With function calling, the model can determine that "this step requires checking inventory," generate a call request, let the system execute it, and feed the result back to the model.
Tool calling is the foundation that allows AI agents to do real work.
Example
A customer asks, "Can this machine ship tomorrow?" The model calls the inventory lookup tool, finds there are 12 units in stock, and answers that it can ship.
Related terms
- AI Agent
- An AI that can read files, call external tools, and complete multi-step tasks on its own, unlike a standard chat AI that only replies with text.
- MCP
- An open protocol that connects AI to external tools and data, enabling AI agents to read and write to databases and trigger business systems.
- API
- Interfaces that allow software programs to interact with each other. Enterprise systems and AI agents use APIs to access capabilities such as large language models, search, image generation, and publishing.
