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

Goes well beyond the annotations, which only declare it is non-read-only and open-world. The description discloses the execution model (headless browser, screenshot, vision detection), an authentication requirement, fair-use rate limits, and a hard environmental constraint (hosted server refuses localhost/private addresses) with two workarounds.

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?

Front-loaded with purpose and the sibling relationship, then layers constraints. It is dense but every section (auth, limits, localhost refusal, tunnel path) carries operational weight; the closing tunnel instructions are slightly verbose but warranted by the constraint.

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?

For an 8-parameter tool with no output schema, the description covers invocation, auth, limits, and environmental limits thoroughly. It does not describe the shape of the returned audit results or how findings are reported, which is the main remaining gap.

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 the schema already documents all eight parameters. The description reinforces the url/tunnel_secret pairing but adds no syntax or format detail beyond what the schema states, 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?

States a specific verb and resource ('pixel-level accessibility audit using Claude vision') and enumerates the exact class of issues it catches with WCAG references, which immediately separates it from DOM-based siblings. An agent can route to it 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?

Explicitly positions the tool relative to scan_page ('complements scan_page — run both for full coverage') and gives concrete alternatives for the local-dev-server case (local MCP vs tunnel). It stops short of stating when visual auditing is unnecessary or inferior to the DOM scanners, so it is clear context rather than full when/when-not guidance.

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