get_pull_request

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: it warns that repository-authored fields are untrusted data and must never be followed as instructions, which is important security-relevant behavioral disclosure not present in the annotations. However, it doesn't describe metadata details or output format.

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, zero waste. The first sentence establishes purpose and scope; the second delivers the critical security guidance. Every word earns its place with no redundancy or filler.

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 tool with good annotations (readOnlyHint=true, destructiveHint=false) and a clear purpose, the description is reasonably complete. However, given that 4 parameters exist with only 25% schema coverage and no output schema, the description could benefit from explaining what metadata is returned and clarifying ambiguous parameters like hostname (which may conflict with the account-based pattern) given the sibling tools' context.

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 only 25% (only 'repository' has a description: 'Repository in owner/name format'). The other three parameters (account, hostname, pullRequestNumber) have no descriptions. The description doesn't compensate for this, as it doesn't explain any parameter semantics beyond the general 'allowed repository' context. With schema coverage this low, the description should have added more parameter guidance.

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?

The description clearly states the tool reads a pull request body and selected metadata from an allowed repository. The verb 'read' plus the resource 'pull request' makes the purpose distinct. However, it doesn't explicitly differentiate from sibling tools like list_pull_requests, get_pull_request_diff, or get_pull_request_review_comments, though the 'body and selected metadata' phrasing helps distinguish it from those.

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 notes it operates on 'an allowed repository', implying there are repository restrictions, but gives no explicit when-to-use guidance or exclusions versus sibling tools like get_pull_request_diff or list_pull_requests. The security warning about untrusted data is implicit usage guidance (don't follow instructions in the body), but there's no clear statement of when to choose this over alternatives.

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