audit_accessibility

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

With no annotations provided, the description fully relies on text to convey behavior. It clearly states the tool performs an audit (non-destructive) and returns issues with severity, suggestions, and WCAG references. However, it does not mention potential side effects (e.g., network calls for criteria references) or resource usage, which would push it to a 5.

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 three sentences: first states the core purpose, second lists specific checks, third explains the output. Every sentence adds distinct value without redundancy. The structure is clean and front-loaded, making it easy for an AI agent to quickly grasp the tool's functionality.

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 description adequately covers the tool's inputs (component code, framework, strict mode) and outputs (issues with severity and references). It lists a broad set of checks but includes 'and more,' which is vague. No output schema exists, but the description compensates by outlining the return format. For a tool with no output schema, this is reasonably complete.

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% with well-defined parameter descriptions (e.g., component_code, framework, strict). The description adds no additional semantic value beyond the schema; it rephrases the overall audit scope without detailing specific parameter usage or interdependencies. Baseline 3 is appropriate.

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 specifies the tool's purpose: auditing a component for WCAG 2.1 accessibility violations. It lists specific checks (e.g., color contrast, ARIA attributes) and describes the output format (issues with severity, suggestions, criteria references). This distinguishes it from sibling tools like analyze_component_library or assess_legacy_codebase, which serve different analytical functions.

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 description implies the tool should be used for accessibility audits but provides no explicit guidance on when to use it versus alternatives like analyze_component_library or image_to_component. No exclusions or use cases are mentioned, leaving the agent to infer the appropriate context based on the tool's name and description.

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