PageSpeed Insights / Core Web Vitals

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

The description goes beyond the readOnly/idempotent annotations by disclosing latency, caching behavior, retry expectations, and a specific failure mode. This accurately sets agent expectations without contradicting the supplied 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?

Every sentence adds useful information: output contents, quota, runtime, caching/retry, and error diagnosis. There is no filler, repetition, or unnecessary detail, making it compact yet dense with relevant guidance.

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 thoroughly covers outputs, latency, retries, and error semantics, which is valuable given there is no output schema. It falls slightly short by not explaining how the strategy and categories parameters alter the returned result set or that defaults are not the full category list.

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 url parameter is implied and categories/top opportunities are loosely referenced, but strategy is never explained and the categories defaults/limiting behavior are not described. With 0% schema description coverage, the description does not carry enough parameter-level meaning.

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 opens with a specific verb and resource: 'Run Google PageSpeed Insights for a URL', then lists the concrete output types. This makes the tool's purpose and scope immediately clear and distinct from sibling SEO/audit tools.

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?

It gives practical operational guidance: set PAGESPEED_API_KEY for a higher quota, expect 15–60 second runs, retry on timeout, and interpret repeated Lighthouse errors as an idle-page issue. Alternative-selection guidance is not explicit, but the usage context is strong.

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