Audit HTML, JSX, or CSS for generic AI clichés, accessibility issues, and 16-pillar design rubric compliance. Evaluate component markup with optional design intent context.
Audit HTML, JSX, or CSS against generic AI clichés, accessibility guidelines, and the 16-pillar rubric.
| Name | Required | Description | Default |
|---|---|---|---|
| componentMarkup | Yes | HTML, JSX, or CSS to evaluate. | |
| contextDescription | No | Contextual design intent. |
Changes observed during successful MCP inspections.
v1.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful scope detail by naming the three evaluation dimensions. However, it does not disclose what the audit produces (findings, pass/fail, scores) or any limits on input size, which matters since there is no output schema.
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?
A single front-loaded sentence naming the action and the criteria, with no filler. It is efficient, though the terse '16-pillar rubric' reference is left unexplained.
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?
The tool is a moderately complex analyzer with no output schema, so the description should indicate the shape of the result (issues found, severity, scores). It also never explains what the 16-pillar rubric is or how contextDescription influences the audit, leaving an agent under-informed about outcomes.
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 both parameters are documented in the schema, and the description merely restates that markup is HTML/JSX/CSS. It adds no meaning for contextDescription or on how markup and context are combined in the evaluation, so the baseline 3 applies.
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 (Audit) and resource (HTML, JSX, or CSS) plus the criteria checked (AI clichés, accessibility, 16-pillar rubric), which clearly separates it from the generate_* and search/fetch_reference siblings. It stops short of explicitly naming a sibling it contrasts with, but an agent can identify the operation without opening the 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?
There is no guidance on when to call this versus the sibling tools (e.g., after generating a genome or test plan, or before generating markup). No preconditions, no when-not-to-use, and no mention of typical workflow position are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.