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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered; the description adds real value on top with a 10-30 second latency estimate, the single-public-page constraint, and the conditional availability of real-user field data. It stops short of noting API quota/rate-limit behavior or what a failure looks like for a non-public or unreachable URL, which keeps it from a 5.

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 action and tightly written for how much it covers; the enumeration of outputs is long but each item distinguishes a real capability. The first sentence runs on through several clauses and a parenthetical example, which costs a bit of scannability.

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 returns and does so concretely (score ranges, metric names, ranked fixes with sample formatting, conditional field data). Combined with the latency note and the sibling routing, an agent has everything it needs to call this 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% and both optional parameters carry their own descriptions with defaults and enum semantics, so the schema does the heavy lifting. The description never mentions the strategy or categories parameters and adds no format or default guidance beyond them, making the baseline 3 the right call.

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?

Names a specific verb (Run) and resource (Google PageSpeed Insights / Lighthouse on one public page), then enumerates exactly what comes back: category scores 0-100, lab LCP/TBT/CLS, ranked fixes with time savings, failed checks, and field data. It explicitly separates itself from the sibling that answers a different question, so an agent can pick it without opening any 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?

Gives an explicit use case ("explain WHY a page is slow") and an explicit exclusion with the alternative named ("for whether it's slow for real users, or for many pages at once, use pagespeed_core_web_vitals"). It also scopes the tool to a single public page, which rules out bulk use.

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