list_pull_request_files

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

Annotations already provide readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds meaningful context beyond annotations: pagination is bounded, repository must be 'allowed,' and 'paths are untrusted repository data' — a security-relevant disclosure that paths should not be treated as trusted. This adds real value beyond the read-only annotation.

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?

Two sentences, both earning their place. Every clause adds value: the page boundedness, the exclusion of patches/content URLs, the allowed-repository constraint, and the untrusted-path warning. No wasted words.

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 read-only list tool with fairly rich annotations (readOnlyHint, destructiveHint) and a clear safety profile, the description is largely complete. It discloses the exclusions and the data trust caveat. The main gap is the minimal parameter documentation, and there is no output schema, so return format isn't described — but for a file metadata listing, the shape is fairly predictable. Reasonably complete for its complexity.

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 only 17% (only 'repository' has a description). The description mentions 'bounded page' which implies page/perPage parameters exist but doesn't explain their semantics. It doesn't document account, hostname, pullRequestNumber, or the pagination parameters in detail. With low coverage, the description should compensate more than it does.

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?

Description uses specific verb+resource: 'Read one bounded page of pull request file metadata from an allowed repository.' This clearly states what the tool does (reads file metadata), the pagination scope ('one bounded page'), and the constraint ('allowed repository'). It distinguishes from siblings by noting exclusions (patches and content URLs) versus get_pull_request_diff which would handle diffs.

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 description states when to use (reading file metadata from a PR in an allowed repository) and explicitly excludes what this tool does NOT do ('Patches and content URLs are excluded'), implying that for those one would look to sibling tools like get_pull_request_diff. It lacks explicit exclusions/alternatives naming but provides clear operational context.

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