Lint markup against the specification

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

The annotations set openWorldHint=false, implying a closed-world result where absence of findings is meaningful. The description says 'Advisory — a clean result is not a certificate of accessibility,' which asserts the opposite: a clean lint result does not rule out accessibility failures. This directly contradicts the openWorldHint annotation.

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 two sentences with no filler. The first sentence is front-loaded with the action and resource, and the list of concrete failure types earns its place. The advisory caveat is short but materially changes how the result should be interpreted.

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?

Given only two simple parameters and a complete schema, the invocation inputs are well covered. The main gaps are the absence of any description of the result shape—there is no output schema—and no explicit differentiation from validate_integration. These are minor for calling the tool but material for interpreting its response.

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 input schema fully documents both parameters, with 100% schema description coverage, so the baseline is 3. The description repeats the HTML/CSS scope and implies component-specific checking but adds no additional syntax, formatting, or semantic detail beyond what the schema already provides.

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 opens with a specific verb and resource: 'Checks HTML or CSS for the accessibility and design-system failures...' and lists concrete failure classes such as missing accessible names, unlabelled inputs, and hard-coded colours. This makes the tool's purpose unmistakable and distinguishes it from siblings like validate_integration without requiring a schema inspection.

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?

The first sentence clearly communicates that the tool applies to HTML/CSS markup, so the input context is implied. However, there is no explicit when-not-to-use guidance and no reference to alternatives such as validate_integration, leaving the agent to infer the routing between validation tools.

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