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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful trait, the 10-30 s latency, which helps an agent budget time, but says nothing about quotas, API key requirements, or failure modes on unreachable URLs.

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?

A single tight sentence with the action front-loaded and the result list and timing appended. No waste, though splitting the timing note into its own clause would make it even easier to scan.

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?

With no output schema, the description usefully names what the response contains and how long it takes, which is enough for an agent to call it correctly. The remaining gap is the meaning of strategy and categories and the overlap with cwv_get_url, so it is good rather than complete.

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 0% across three parameters, so the description must compensate and does not. It mentions only 'a URL' and never explains the mobile/desktop strategy or what the categories array selects; the enum values and defaults are visible in the schema, but their effect on the returned report is left unexplained.

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 (run Lighthouse via PageSpeed Insights for a URL) and enumerates what comes back: category scores, lab metrics, field data, top opportunities. It stops short of differentiating from the sibling cwv_get_url, which also surfaces field data, so an agent cannot fully tell them apart from the description alone.

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 'Takes 10-30 s' note implies this is a heavier, slower call that should be used deliberately, but the description never states when to pick this over cwv_get_url or cwv_get_origin, nor any exclusions. Usage is only inferable from the mention of a full Lighthouse audit.

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