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

Annotations already cover read-only, idempotent, non-destructive and open-world, so the bar is lower. The description still adds genuinely useful interpretation semantics: each point is a 28-day trailing window, consecutive points overlap, and a step change marks a real shift. This is real context an agent cannot get from the annotations or schema.

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?

Dense but front-loaded: what it returns, then the source, then the interpretation caveat. Every sentence carries information, though the single long paragraph could be tightened slightly.

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 must (and does) explain the return shape: a weekly series of 75th-percentile values with collection period dates, plus the 28-day overlap caveat. Complete enough for an agent to call and interpret it; only the sibling routing remains implicit.

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%, with each parameter (url, origin, metrics, form_factor) documented including the enum and the mutually-exclusive url/origin guidance. The description adds no per-parameter syntax or format detail beyond what the schema already carries, so the 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: how a site's/page's real-user Core Web Vitals have moved over ~40 weeks from the CrUX history API, and names the exact return ('weekly series of 75th-percentile LCP, INP and CLS'). It distinguishes itself conceptually from time-series siblings (crux_query_origin/url) but never names them, so the differentiation is implied rather than explicit.

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?

Gives clear when-to-use context: 'AUTHORITATIVE for "did the performance work actually help" and for spotting the week a regression landed.' Strong positive selection guidance, but no explicit when-not or named alternative (e.g., use crux_query_origin for a single current snapshot), so it doesn't reach 5.

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