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

Annotations already establish read-only, idempotent, non-destructive, open-world behavior, so the bar is lower; the description goes well beyond by disclosing the no-data limitation for low-traffic pages, the origin fallback, the ~30 s latency of the lab test, and the ~6-month span of the history trend. These are exactly the operational traits an agent needs to set expectations and avoid misinterpreting empty 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?

Content is front-loaded with what the tool returns, and most clauses earn their place (data source, metrics, split thresholds, fallback). It is a dense pair of run-on sentences, so it is slightly heavier than ideal, but very little is wasted.

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 carries the full burden of explaining return values, and it does: metrics, percentile, good/needs-improvement/poor buckets, LCP breakdown components, and the empty-result case. Combined with the annotation-covered safety profile and 80% schema coverage, an agent has everything needed to call and interpret it correctly.

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?

With 80% schema coverage the baseline is 3, but the description adds meaning the schema lacks—notably that history=true yields a weekly trend over ~6 months (the schema gives no description for history at all) and how url vs origin select page vs site scope. It reinforces rather than merely repeats the lab and form_factor semantics.

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 names the specific data source (Chrome UX Report / CrUX field data), the resource (a page via url or a site via origin), and the exact metrics returned (LCP, INP, CLS with 75th percentile and good/needs-improvement/poor splits, plus FCP, TTFB, and LCP sub-parts). An agent can distinguish this from every sibling (page_audit, ga4_*, gsc_*) without opening the schema.

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 clearly explains the two addressing modes (url for one page, origin for a whole site), what history=true and lab=true add, and the fallback rule when a page has too little Chrome traffic (origin is tried). It stops short of naming alternatives among siblings or stating when-not-to-use it, so 4 rather than 5.

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