lighthouse_audit

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

Annotations declare readOnlyHint=false, signaling this is not a pure read operation, and the schema's mode description already notes that navigation reloads the page and outputDirPath indicates report file output. The tool description itself adds little behavioral context beyond the performance exclusion, but it does not contradict the annotations.

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?

Two short sentences carry the full purpose, category scope, exclusion, and sibling alternative with no filler. The main action is front-loaded, and the performance carve-out is stated immediately after.

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 plus schema covers purpose, scope, parameters, and the main sibling alternative, but with no output schema it leaves the report shape and return value unspecified. The description also relies on the schema to communicate side effects like navigation reloading and report output, which are important for an agent to anticipate.

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?

The input schema has 100% parameter description coverage, so every parameter's meaning is already documented. The tool description adds no parameter-level detail beyond that, which lands it at the baseline score of 3.

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 uses a specific verb ('Get') and resource ('Lighthouse score and reports'), and enumerates the exact audit categories: accessibility, SEO, best practices, and agentic browsing. It explicitly excludes performance and names the sibling performance_start_trace, making the tool's scope unambiguous.

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 states both what this tool is for and what it is not for: 'This excludes performance. For performance audits, run performance_start_trace.' This gives an agent a clear decision rule and a direct alternative when the audit request is performance-focused.

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