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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description goes well beyond them: it discloses third-party data flow ('The address is sent to Google, which loads the page'), the no-side-effect guarantee ('does not edit the target website or submit forms'), the 20–40 second latency, and 12-hour result caching. Those latency and caching traits directly change how an agent should sequence and retry calls, which annotations cannot convey.

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?

Six sentences, front-loaded with the triggering conditions before the mechanics and the exclusions. Every sentence carries distinct operational value — engine, return payload, data-sharing, side-effect boundary, latency/caching, anti-patterns — with no filler or repetition.

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?

Despite having no output schema, the description enumerates the return payload (performance/accessibility/best-practices/SEO scores, lab measurements, real-user CWV when available, top-impact fixes). Combined with stated latency, caching, and access limits, an agent has everything needed to decide, call, and wait 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?

Schema coverage is 100%, so both parameters (url and device) are already fully documented in the schema, including the mobile default and the rationale that Google ranks on mobile. The description restates the public-page/no-credentials constraint on the URL but adds no new syntax, format, or interaction detail beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

Opens with a precise verb+resource ('how fast a public web page is') and enumerates the specific questions it answers (Core Web Vitals, Lighthouse, what to fix). It also names the underlying engine (Google PageSpeed Insights) and the exact score categories returned, so an agent can tell instantly this is a performance audit and not the case-study, booking, or scoping siblings.

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 explicit when-to-use triggers ('someone wants to know how fast... why it's slow... what to fix') and explicit exclusions ('Don't use it to check whether a site is up, for security scans or for keyword research'). It also states the eligibility boundary — public pages only, no localhost, no login-gated pages, no URLs with credentials — which is the main pre-call gate an agent must check.

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