review_changes

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is lower, yet the description adds real substance: unchanged-line findings are omitted and never resolved, and validation commands and live DB access are never enabled. This tells the agent what the tool deliberately won't do, which is not in the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the purpose and verdict, then scope behavior, then safety defaults. No sentence restates another and nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return burden and does so: it names the three verdict values and explains the diff-scoped finding model. Combined with the fully described parameters and safety annotations, an agent has everything needed to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter (base, path, format) is fully documented in the schema, so the structured data does the work. The description contributes no additional parameter semantics such as ref syntax or path constraints, which is acceptable at this coverage level (baseline 3).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('review changed code') plus the concrete output ('PR-ready verdict' with APPROVE/COMMENT/REQUEST_CHANGES). The phrase 'narrows findings to added diff lines' implicitly separates it from audit_codebase, but no sibling is named explicitly, leaving the agent to infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies a pre-PR review context through 'PR-ready verdict' and diff-scoping, but never states when to choose this over verify_changes, build_receipt, or audit_codebase. Usage is inferable rather than guided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.