List pull request reviews

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds real substance on top by scoping what each review record contains (verdicts and summary bodies) and disclosing that inline comments are truncated to a count — a non-obvious data-fidelity caveat. It stops short of describing ordering or pagination behavior beyond naming the params.

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?

One dense, front-loaded sentence that leads with the resource and scope before the parenthetical. The parameter parenthetical is slightly redundant against a fully documented schema, keeping it just shy of a 5.

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?

For a 5-parameter read-only list tool with no output schema, the description tells the agent what comes back (verdicts, summary bodies, inline comment count) and which parameters exist, which is nearly sufficient. Ordering, total counts, and pagination mechanics remain unstated.

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 description coverage is 100%, so the schema already documents owner, repo, index, page and limit. The parenthetical '(owner/repo/index; optional page/limit)' merely restates required vs optional status without adding format or semantics, which is the baseline-3 case.

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 (list the reviews on a pull request) and then enumerates the exact payload — approve/request-changes/comment verdicts plus summary bodies. The note that inline comments appear only as a count cleanly separates it from sibling tools like list_pull_request_files and get_pull_request_diff.

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?

The reading context is implied by the content scope, and the 'inline line comments only as a count' note signals that detailed inline discussion lives elsewhere, but no sibling is named and no when-not-to-use condition is given. An agent must infer that create_pull_request_review is the write counterpart.

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