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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description usefully clarifies that 'auto-fix' means returning fixed classes/modifiers rather than mutating anything, but it does not explain error-vs-warning semantics (which the allowCustomClasses param implies exist) or what the response contains.

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?

One tight sentence with the core check front-loaded and the optional auto-fix trailing after a semicolon. Nothing is redundant or buried.

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 burden of saying what comes back, and it does not — an agent cannot tell whether it receives a boolean, a list of violations, or the fixed class string, nor how warnings differ from errors. For a validation tool whose whole value is the report, that is a real gap despite complete annotations and schema.

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; all five parameters are already documented in the schema, including the intentVariant options and the allowCustomClasses error/warning distinction. The description only echoes autoFix and intentVariant at a high level, adding little beyond structured data.

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?

Specific verb (check/validate) plus a precise resource (button class string) and the two defect classes it looks for (variant conflicts, token misuse), plus the optional auto-fix. It is clearly distinguishable from a generic audit tool, though it never names its closest sibling, generate_button_classes.

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?

Usage is implied rather than stated: an agent can infer this is the tool to call when it already has a class string that needs checking. There is no explicit guidance on when to prefer this over generate_button_classes, no prerequisites, and no note on when auto-fix should be turned off.

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