Review Diff

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond annotations: it reviews ONLY added lines and lists concrete check categories (secrets, empty catches, @ts-ignore, XSS sinks, disabled TLS, await-in-loop). No contradiction with annotations.

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 sentences, front-loaded with the primary purpose, followed by the scoping constraint and check list. Zero wasted words; the check list is compact and informative without over-elongating.

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?

Complete for purpose and scope, but two gaps remain: there is no output schema, so the description carries the burden of explaining the return format and doesn't; and the 'new secrets' flagging overlaps with the secret_scan sibling without disambiguation, leaving an agent to guess which tool to invoke.

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% with both base and path documented, so baseline is 3. The description reinforces the base=HEAD default (uncommitted changes) and the diff target semantics, but adds little meaning beyond what the schema already provides.

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+resource ('Diff-aware code review' of uncommitted changes or branch comparison). Clear scope: reviews only ADDED lines. However, it doesn't explicitly differentiate from the overlapping secret_scan/security_scan siblings that also flag security issues like 'new secrets'.

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?

Provides clear context for when to use: 'uncommitted changes or a branch comparison'. But no explicit when-not guidance or alternative routing despite several overlapping security/scan siblings. The 'way a human reviewer reads a PR' framing implies usage but doesn't exclude tool boundaries.

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