run_lighthouse

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

The description fully discloses that the tool launches its own headless Chrome, ignores session/auth state, and handles Node.js detection along with failure recovery commands. Since no annotations are provided, this transparency is critical and well-covered.

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 highly concise, front-loads the main purpose, and each sentence adds value—covering behavior, prerequisites, return values, and error handling without 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 running Lighthouse (Node.js, Chrome), the description covers essential context: return values, metrics, Chrome isolation, and setup requirements. The lack of an output schema is compensated by detailing what is returned (scores, metrics, failed audits, saved report).

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?

All 4 parameters have clear descriptions in the input schema (100% coverage). The description adds context about the tool's outputs but does not augment the meaning of individual parameters beyond the schema, so baseline score of 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 states the tool runs a real Google Lighthouse audit against a URL, returning scores, Core Web Vitals, and saving a full JSON report. It has no clear sibling duplicates; among many session/tool/test tools, this one is uniquely identified.

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 explains prerequisite (Node.js) and behavior (headless Chrome, no session/auth), as well as auto-detection and error recovery. It does not explicitly state when to avoid use, but the context is sufficient for correct invocation.

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