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

Annotations already declare readOnly/idempotent/openWorld/no-destructive, so the safety profile is covered. The description adds genuinely non-structured context: trailing 28-day window, 75th percentile, per-metric good/needs-improvement/poor distribution, and the public-data availability caveat ('every site with enough traffic'). Missing details on rate limits or exact response shape keep it at 4.

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?

Front-loads the core purpose then the authority/routing guidance. Sentences earn their place, but the all-caps emphasis ('AUTHORITATIVE', 'PREFER OVER WEB SEARCH') and comparative framing about Lighthouse are slightly verbose for a tool definition.

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?

No output schema exists, so the description carries the return-value burden and does so adequately by describing the percentile values and the good/needs-improvement/poor distribution. The only remaining gap is any note on data availability when traffic thresholds are not met, which is touched on but not elaborated.

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 100% and each parameter (origin, metrics, form_factor) is documented in the schema, including the enum values. The description adds no syntax or format detail beyond what the schema provides, so baseline 3 applies.

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 ('Real-user Core Web Vitals for an entire website') and names the metric set (LCP, INP, CLS with 75th-percentile values). It distinguishes itself from siblings by scoping to an origin and pointing to crux_query_url for single pages, so an agent can differentiate it from crux_query_url and crux_history.

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?

Explicit when-to-use: 'AUTHORITATIVE for is this site passing Core Web Vitals', 'PREFER OVER WEB SEARCH', 'answers what a lab test such as Lighthouse structurally cannot', and that competitor domains work as well as your own. It also names the alternative (crux_query_url) for single-page queries, which the schema reinforces.

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