review_design_pull_request

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and openWorldHint=false, so the safety profile is covered. The description usefully clarifies that four distinct mutation outcomes exist, but it never says what each verdict does downstream (e.g. whether REJECT closes the PR, whether REQUEST_CHANGES blocks merge, whether a review can be changed later) or that user_id is checked server-side. That is a real gap for a destructive operation, but the enumerated decisions are genuine added context beyond the annotations.

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?

The first sentence is tightly front-loaded and earns its place. The second sentence is pricing/packaging boilerplate that consumes roughly half the description without helping an agent decide or invoke, which is wasted space.

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 destructive, four-parameter mutation with fully documented parameters and no output schema, the description covers the action space adequately. It is incomplete on the observable consequences of each decision and on required authorization beyond what user_id's schema text implies, which an agent would want before submitting a REQUEST_CHANGES or REJECT.

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% and each parameter already documents its meaning, including the body requirement for COMMENT and the user_id identity fallback, so the schema carries the semantics. The description adds no additional constraint on pr_id, body, user_id, or the decision values. Baseline 3 applies.

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 first sentence gives a specific verb (review) and resource (design change) and enumerates the four outcomes (comment, approve, request changes, reject), so the agent knows exactly what action space this tool covers. It does not distinguish itself from adjacent siblings such as get_design_pull_request, withdraw_design_pull_request, or evaluate_pr_approval, so it stops short of a 5.

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?

There is no guidance on when to pick this tool over list_design_pull_requests, get_design_pull_request, or withdraw_design_pull_request, nor any stated prerequisites such as needing an open PR or review permission. The only extra sentence is subscription-tier marketing, which does not tell the agent when to use or avoid the tool.

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