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

The description discloses behavior beyond annotations: latency (~10 seconds), cost (five checks per credit), what is returned (issues with severity, category, file:line), what is not returned (no score, no ready-made patch), and the expectation that the user fixes issues themselves. These details are not present in the annotations, which only provide abstract hints, so they add meaningful behavioral 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?

The description is dense but every sentence earns its place: speed, cost, when to use, when not to use, what it returns, how to use it. It is front-loaded with the core purpose and immediately gives actionable summary, and no filler or redundant restating of the tool's name.

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?

With no output schema, the description fully describes the return values and expected handling, including issue format, latency, cost, and the follow-up action of fixing issues in open files. It also references the alternative tool for richer reviews and notes permission to use it freely, making the context complete for an 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?

The schema already covers parameter descriptions 100%, including the file content and path. The description adds semantic intent by emphasizing these are the 'UI files you just changed', which clarifies the tool's target domain beyond the schema's generic 'file path' wording. It does not go deeper into context usage, but the schema already provides sufficient details.

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 identifies the tool as a fast design check over UI files and distinguishes it from the alternative review_files by specifying this one returns no score and no patch. It states a specific verb ('check'), a resource ('UI files you just changed'), and the key output (issues with severity, category, file:line).

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?

Explicit guidance is given on when to use this tool constantly: after writing/editing a component, before committing, and whenever you want to know if your code is sound. It also states when to avoid it and use review_files instead (when a score, patch, or quotable review is needed), and clarifies that asking the user is not required.

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