Definition
A tool schema is the structured definition that tells a language model what an external tool does and how to call it. It is the contract behind function calling, the mechanism that lets an LLM step outside text generation to query a database, run code, or hit an API. The schema names the tool, describes when to use it, and specifies each parameter, its type, and whether it is required, almost always expressed as JSON Schema.
Anatomy of a tool definition
Every tool definition has three load-bearing parts. The name is a stable identifier the model emits when it wants to invoke the tool. The description is plain-language guidance the model reads to decide whether and when the tool applies; this field does more work than people expect, because a vague description leads to wrong or missed calls. The parameters object is a JSON Schema declaring the inputs, with types, enums, and constraints. Anthropic's API names this field input_schema, while OpenAI nests it under a parameters key, but both rely on the same JSON Schema foundation and both return a structured, machine-readable request rather than free text.
Why the schema is the safety boundary
The schema is where reliability and control live. Typed, constrained parameters let your application validate every call before executing it, so a model cannot, for instance, pass a string where an integer is required. For anyone wiring an agent into systems they own, a tight schema is the difference between a tool the model uses correctly and one it misuses. Clear descriptions and minimal, well-typed parameters are the core best practice.
Tool schemas are the building block beneath autonomous agents and underpin cross-system coordination such as Agent-to-Agent (A2A).
In Simple Terms
A tool schema is the structured definition that tells a language model what an external tool does and how to call it. It is the…