core_web_vitals

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

Annotations already cover the read-only/open-world safety profile, and the description layers on genuinely new behavior: a 10–30 second runtime per run, and the caveat that real-user field data only appears "when Google has enough visits." It does not cover failure modes (e.g., what happens for an unindexed or invalid page), which keeps it below a 5.

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?

Four tight sentences, front-loaded with what the tool returns and then the page/site/strategy semantics. Every clause earns its place — even the runtime note is actionable scheduling information rather than filler.

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 maps the response shape (page_field and site_field with LCP/INP/CLS and Google's rating; lab with performance score, LCP, CLS, TBT, FCP, Speed Index). What remains thin is input formatting guidance for `site`/`page` and any error behavior.

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%, so the description must carry the load — and it largely does, giving the default for `page`, the meaning of `page` vs. `site` scoping, and the allowed values for `strategy` ("mobile" or "desktop") that the schema does not enumerate. The `site` parameter's expected format (domain vs. full URL) 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+resource: fetches Core Web Vitals for a page from PageSpeed Insights, with an explicit default (the site's home page). It also enumerates the two result families (real-user field data vs. a single Lighthouse lab run), so an agent knows precisely what it gets back. No sibling tool overlaps this performance-metric niche.

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 implies the usage context (auditing page performance, choosing mobile vs. desktop) and discloses a 10–30 second cost, but never states when to call this instead of something else or when-not to call it. The disambiguation between field and lab data is implicit rather than framed as a selection rule.

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