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

The description adds useful behavioral context beyond annotations: speed (~10 seconds), cost (one review credit per five checks), absence of score/patch, and that the agent must fix issues itself. It does not explicitly state whether the tool modifies files, but the guidance to fix things in already-open files implies no patch is returned. No contradictions with 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 description is front-loaded with purpose and return value, then covers cost, usage frequency, permissions, limitations, and alternatives. It is somewhat wordy, but each sentence adds decision-relevant information for an agent.

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 adequately explains the return format (severity, category, file:line). It covers cost, timing, when to use, and the main sibling alternative. It does not mention verify_fixes or error cases, but the tool is simple enough that this is not a critical gap.

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%, so the input schema already documents the files array and optional context. The description adds only the framing 'UI files you just changed' but does not elaborate on parameter syntax or content requirements, which is acceptable since the schema carries that burden.

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 uses a specific verb-resource pair: 'Fast design check over the UI files you just changed.' It clearly states the return value (issues with severity, category, and file:line) and explicitly distinguishes itself from review_files for score/patch needs.

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?

It explicitly states when to use it: 'after writing or editing a component, before committing, whenever you want to know if what you just wrote is sound.' It also gives a clear exclusion: use review_files when the user wants a score, patch, or quotable review.

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