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

Annotations already establish that this is a read-only, idempotent, non-destructive call, so the safety profile is covered. The description adds genuine behavioral context beyond that: the field-vs-lab data limitation and the 'not_measured, never 0' sentinel convention for missing lab metrics, which is essential for interpreting results.

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?

Three tightly scoped sentences with the core purpose front-loaded, followed by two scope exclusions and one return-value caveat. No filler, and each sentence carries information an agent needs.

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 and only 50% parameter coverage, the description does most of the heavy lifting: it defines scope, data limitations, and result semantics. It is nearly complete, missing only hints about what metrics are returned or the latency/cost profile of a PageSpeed Insights call.

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 sits at 50%: 'url' is documented but the 'strategy' enum carries no description. The phrase 'one URL and one strategy' implies the single-value cardinality of both parameters, but adds no syntax or value meaning beyond the schema, so the baseline 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?

States a specific verb and resource ('Core Web Vitals via PageSpeed Insights') and precisely bounds scope to 'one URL and one strategy', which separates it from site-wide siblings like crawl_site and audit_page. It stops short of naming an actual sibling, so differentiation is achieved only by negative scope statements.

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?

Two explicit exclusions carve out when this tool is wrong: it does not measure field (CrUX) data unless PageSpeed supplies it, and it does not audit the rest of the site. That is clear usage context, but the description never names the alternative tool an agent should reach for instead.

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