Agents & tools · Glossary term

What is Tool Contract?

The complete agreement for a tool boundary: purpose, typed inputs, outputs, validation, permissions, side effects, errors, timeouts, idempotency, and evidence returned to the caller.

Why does Tool Contract matter?

A schema tells a model what fields exist; a contract tells the system when the tool is safe and how failures must be handled.

Tool Contract in practice

Define a file-write tool with an allowed root, expected base revision, maximum size, dry-run mode, explicit conflict errors, and a returned patch hash.

What is the common confusion about Tool Contract?

A JSON Schema is part of a tool contract, not the whole contract.

Learn Tool Contract in the course

Start with

  • Tool Use and Function Calling

    Toolformer (Schick et al., 2023) started self-supervised tool annotation. Berkeley Function Calling Leaderboard V4 (Patil et al., 2025) sets the 2026 bar: 40% agentic, 30% multi-turn, 10% live, 10%…

    Phase 14: Agent Engineering

Lessons that name Tool Contract in a title or section

  • MCP Tool Contracts and Content

    A tool is safe to automate only when discovery, arguments, results, pagination, and transport metadata agree on one contract. Define tool inputs and outputs with JSON Schema 2020-12.

    Phase 13: Tools & Protocols

Taught in Phase 14: Agent Engineering.

Also covered in Phase 13: Tools & Protocols.

  • Function CallingA provider or application interface through which a model emits a structured request naming a tool and its arguments.
  • Structured OutputModel output constrained or validated against a machine-readable schema so application code can consume fields without parsing free-form…
  • Least PrivilegeGiving a model, agent, tool, or user only the permissions required for the current task, for only as long as those permissions are needed.
  • IdempotencyThe property that repeating the same operation with the same identity does not create additional side effects beyond the first successful…
  • AgentA software system that lets a model select actions toward a goal, observe tool or environment results, and continue under an orchestration…
  • Agent HarnessThe runtime around a model that assembles context, exposes tools, manages state, enforces limits, records traces, and decides when the…
  • Instruction HierarchyA rule set for resolving conflicts among instructions from sources with different authority, such as application policy, users, and…
  • MCP (Model Context Protocol)An open JSON-RPC protocol for a host to connect to servers that expose tools, resources, prompts, and extensions through defined request,…
  • Multi Round-Trip Request (MRTR)An MCP request pattern in which an operation returns `resultType: input_required` with one or more `inputRequests`, then the client…
  • Prompt InjectionAn attack or failure mode in which untrusted content influences a model to disregard intended instructions, expose data, misuse tools, or…
  • Stateless MCPThe MCP 2026-07-28 request model in which every request carries the protocol version and client capabilities in `params._meta`, while…

More terms in Agents & tools

Open the Agents & tools list in the glossary

This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.