review_pull_request

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

Annotations show readOnlyHint=false and idempotentHint=false, meaning this is a mutating non-idempotent operation. The description adds value by noting 'This never merges it' to prevent confusion with merging, and the body requirement for COMMENT/REQUEST_CHANGES. However, it doesn't disclose what happens on approval (e.g., does it block/wait?), whether the review is associated with the authenticated user, or any side effects on the PR status. With partial annotations (destructiveHint=false which conflicts with the mutating nature), the description could add more nuance but does add some useful safety context.

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, front-loaded with the primary action and key constraint ('This never merges it'). The second sentence adds the body requirement. Every sentence earns its place with necessary behavioral qualifiers.

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 review-submission tool with 4 required params, no output schema, and only 17% schema description coverage, the description covers the core distinction (review vs merge) and body constraints. However, it doesn't clarify the relationship to sibling tools like comment_pull_request or create_pull_request_review_comment, which could be confused for similar operations. It's reasonably complete for the core action but leaves the tool-selection nuance to the agent.

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 17% - only the repository parameter has a description. The description does explain the 'event' enum values (APPROVE, REQUEST_CHANGES, COMMENT) and the body requirement for two of them. However, it doesn't explain account, hostname, or pullRequestNumber parameters. The description partially compensates for the low schema coverage by explaining the key enum and the body-requirement relationship, but it doesn't cover all parameters.

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 action ('Submit an APPROVE, REQUEST_CHANGES, or COMMENT review') and the resource ('to an existing pull request'). It explicitly disambiguates from merge_pull_request by stating 'This never merges it.' It also clarifies that the event types are the review decision options.

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 mentions that COMMENT and REQUEST_CHANGES require a body, which is useful context. However, it doesn't give explicit guidance on when to use this tool vs. siblings like comment_pull_request or create_pull_request_review_comment. There are many related pull request tools (merge, comment, review comment, etc.) but no alternatives or exclusions are named.

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