audit_lighthouse

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

With no annotations, the description carries the full burden. It reveals that Lighthouse audits by URL and reloads the page, and that it requires the Node engine runner. This is valuable behavioral context beyond simple CRUD.

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 extremely concise: two short sentences that front-load the purpose and key usage details. Every word adds value with no 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 complexity of auditing tools and the presence of an output schema, the description is adequate but not thorough. It fails to explain the return format or how the 'level' parameter affects results, assuming the agent will rely on the output 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 0%, so the description must compensate. It clarifies that url, html, and session_id are mutually exclusive inputs, but does not mention the 'level' parameter or its default 'AA'. This adds partial value beyond the schema's basic type info.

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 it audits with Google Lighthouse for accessibility. It specifies the engine and mentions input options (url, html, session_id), distinguishing it from siblings like audit_axe or audit_pa11y by specifying 'Lighthouse engine only'. However, it doesn't elaborate on what Lighthouse checks beyond accessibility.

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 provides some usage guidance: 'Provide one of: url, html, or session_id' and 'Requires the Node engine runner.' But it does not explicitly state when to use this tool over alternative audit tools (e.g., when to choose Lighthouse over axe or pa11y), leaving the agent to infer.

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