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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds genuinely non-obvious behavior beyond them: a 24-hour server-side cache keyed on (url, strategy) with 'free + instant' repeat calls, and a cap of the top 8 opportunities ranked by potential savings. It does not mention any API key, quota, or rate-limit behavior for uncached runs.

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-loaded with the verb and target, then structured into returns / caching / companion-tool sections. Slightly redundant to enumerate scores and metrics since an output schema exists, but the enumeration is compact and the 'top 8' truncation note is worth its space.

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?

For a two-parameter read-only audit tool with a full output schema and safety annotations, the description covers the remaining gaps an agent needs: which data flavor it returns, caching semantics affecting repeat cost, and the truncation of opportunities. Nothing required to invoke it correctly is missing.

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 the `strategy` parameter already documents mobile vs desktop throttling profiles in detail, including the Moto G4-class CPU emulation. The description adds only the cache-key framing '(url, strategy)', which is marginal semantic value over the schema, so the baseline of 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 and resource ('Run a Google PageSpeed Insights (Lighthouse) audit on a public URL') and immediately scopes what kind of data it produces (lab data) versus the field-data sibling. An agent can distinguish it from pagespeed_field_data without opening either 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?

Explicitly names the companion tool `pagespeed_field_data` and states what it returns instead ('real-user CrUX data from the same underlying call'), so the lab-vs-field routing decision is clear. It also flags a hard constraint ('localhost / staging URLs won't work'). It does not address other plausible siblings such as batch_inspect_urls for multi-URL runs, so it stops short of full exclusion guidance.

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