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

readOnlyHint=true already establishes this is a non-mutating check, so the safety bar is met by annotations. The description adds the useful scope of what gets flagged, but never says what the tool returns (a list of violations? a pass/fail?) despite no output schema existing.

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 purpose and closing with the usage trigger; the defect list is dense but every item is meaningful. No filler or repetition of the tool 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?

For a single-parameter read-only validator this is close to adequate, but with no output schema the agent cannot predict the response shape, and the description never states it. The absence of any detail on returned violations is the remaining 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 0% and the single 'markup' parameter has no schema-level documentation, so the description must compensate. It does partially, by clarifying the accepted input is HTML or JSX, but adds no format, size, or path-vs-inline guidance.

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 (checks) and resource (HTML or JSX markup) and enumerates concrete defect categories: nonexistent classes, variant classes, data-* values a class does not react to, hand-written colors, and data-theme/data-mode misuse. It is trivially separable from the all-get_* siblings.

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 gives an explicit timing directive – 'Run it on markup you wrote before finishing' – which tells the agent this is a pre-completion validation step. There is no statement of when not to use it or a named alternative, but none of the siblings offer overlapping validation.

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