visual_audit

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

With no annotations, description fully bears burden. It discloses the process: takes URL, opens headless browser, screenshots, runs vision detection. Also warns about account requirement and paid nature, which are critical behavioral traits.

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?

Description is relatively long but well-structured with bullet points and clear separation of purpose, process, and prerequisites. Each sentence adds value, though slight verbosity could be trimmed.

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?

Missing description of output or return value. For a tool that runs an audit, it doesn't explain what the agent receives (e.g., a report, issues list, score). With no output schema, this is a notable gap, but other aspects (usage, parameters) are well-covered.

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 baseline 3. Description adds no extra meaning to parameters beyond what schema already provides. The text only mentions 'takes a URL' but does not elaborate on optional parameters.

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?

Description clearly states 'Pixel-level accessibility audit using Claude vision' and lists specific issues it detects (icon contrast, focus visibility, etc.). It distinguishes from sibling tool scan_page by stating it complements it and suggests running both for full coverage.

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?

Explicitly explains when to use (for vision-based checks), how it complements scan_page, and prerequisites including account requirement and authentication methods. Differentiates from DOM-based free tools.

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