evaluate_design_benchmark

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

Without annotations, the description carries the transparency burden. It discloses return values but does not explicitly state side-effect-free behavior, limitations, or any required context. The verb 'evaluates' implies read-only, but the description could be more explicit about its safe, non-mutating nature.

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 a single, well-structured sentence that efficiently covers the action, target standard, input types, and output categories. No filler or redundancy.

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 the absence of an output schema and annotations, the description sufficiently explains what the tool returns. However, it lacks any usage context or differentiation from sibling tools, making it slightly incomplete for a tool in a crowded design-related ecosystem.

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 each parameter already has a description. The tool description adds no extra parameter-specific meaning beyond what the schema provides, though it confirms the input types mentioned in the codeOrMarkup parameter.

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 clearly states the tool's function: evaluating UI code, CSS, or Tailwind markup against Level-5 Claude Design standards. It also lists returned artifacts (overall score, sub-scores, strengths, recommendations), which distinguishes it from sibling audit tools like anti_slop_audit and accessibility_audit.

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?

No guidance is provided about when to use this tool versus alternatives. It doesn't describe ideal scenarios, exclusions, or how it relates to sibling tools such as pipeline_design or invoke_design_agent, leaving usage entirely to inference.

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