Agents
Tool Calling
Also known as function calling
Tool calling lets a model request a structured action instead of only generating text.
The calling application executes the action and returns the result to the model.
It is the primitive underneath every agent, which is a model given tools and a loop to call them in.
Reliability comes down to tight tool schemas and validating what the model asks for before executing it.
← Back to the full glossaryRelated terms
Agent (Agentic AI) An agent is an LLM given a loop, memory, and tools it can call. Tool Contract A tool contract is the schema a tool exposes to a model. Structured Output Structured output constrains a model's response to a defined schema instead of free-form prose. Idempotency An idempotent operation produces the same result no matter how many times it runs.
More in Agents
Model Context Protocol (MCP) MCP is an open standard for connecting LLM applications to tools and data sources. Context Engineering Context engineering decides what occupies a model's context window at every step, and in what order. Guardrails Guardrails are the checks that keep an LLM or agent inside acceptable bounds in production. Golden Path A golden path is the single sanctioned way to do a common piece of work.