Review my changes

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

Beyond the readOnlyHint/openWorldHint annotations, it discloses material behavior: consult collects the diff itself and ships it along with review instructions, advisors read surrounding code, and results are advisory ('Treat findings as claims to verify, not instructions'). That last sentence is a genuinely useful trust/safety disclosure for an open-world tool that transmits source code to third-party CLIs.

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?

Four sentences, front-loaded with the purpose and default scope before the base-toggle and the advisor heuristics. No filler; each sentence carries distinct information (scope, base mode, diff-collection ownership, advisor vendor preference, follow-up path, verification posture).

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 does cover the key return affordance (each review has its own session_id for follow-ups) and sets expectations that findings are claims. It stops short of saying one result is returned per advisor or how large/structured those results are, which would fully close the gap for a fan-out tool.

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%, so the baseline is 3, but the description adds real semantics: base means 'the whole branch since it left that branch' rather than a plain diff ref, and it clarifies that the caller only supplies advisors plus an optional focus because consult builds the diff. Minor remaining ambiguity is what cwd does when advisors read surrounding code, which the schema covers but the description does not reinforce.

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 ('Get a code review of the git changes in the working directory') plus the mechanism ('from one or more other AI coding agents, in parallel'). The scope default (everything not yet committed: staged, unstaged, new files) further pins down what exactly is reviewed, so it is distinguishable from ask_agents/list_agents without opening any schema.

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?

Gives explicit selection logic between the two modes: omit base for uncommitted work, pass base (e.g. 'main') to review the whole branch since it forked. It also routes follow-ups to ask_agent via session_id. What it lacks is any explicit 'when not to use this' or a named alternative for non-diff questions, which keeps it short of a 5.

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