Review UI Code

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

Annotations already cover read-only/idempotent safety, but the description adds substantial context: findings are deterministic with exact line numbers and fixes, it accepts files by path and reads from disk, and it explicitly declines to judge rendered hierarchy or semantic color roles. That limitation disclosure is the kind of honesty that prevents an agent over-trusting a pass.

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?

Instructions are front-loaded and the capability list is scannable, but the description is long and has some redundancy — the fix-and-re-call loop is stated twice and the catch list partially overlaps what findings would show anyway.

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 carries the return-value burden itself and does so: findings with line numbers and fixes, plus severity guidance ('fix every critical and serious finding'). Given the complexity of a multi-language static reviewer, an agent has everything needed to call it and interpret the result.

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 100% so the baseline is 3; the description earns above that by explaining a workflow choice rather than restating fields — leaving out `content` to have the tool read the file from disk, and pairing a component with its own icon/CSS-dependency files so findings can name the fix. The 24-file cap and the analytics-only `context` param are left to the schema.

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 names a specific verb and resource — deterministic UI/UX review of React source, CSS, and SwiftUI views — and explicitly positions itself as the mechanical half of a pair with get-review-rules (the judgment half). An agent can distinguish it from the many get-*-guide siblings without opening any schema.

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 states when to call ('on every UI file you write or change... before you present the result'), what to include beyond the obvious page ('markup of every mock product screen or embedded panel too', 'include the layout or font-loader .ts/.tsx module in the same call'), and what it cannot do, redirecting to rendered inspection afterward. It also names the alternative (get-review-rules) and the post-fix loop.

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