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

No annotations are supplied, so the description carries the full disclosure burden. It does disclose what comes back (Core Web Vitals, 0-100 score, top opportunities), which is genuinely useful. It says nothing about the cost profile of a PageSpeed Insights call (multi-second latency, per-strategy calls, quota or API-key requirements) or failure behavior for unreachable URLs.

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?

Two compact clauses, front-loaded with the provider and resource, followed by the return payload. No filler, no marketing, nothing restated from the schema.

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 2-parameter tool with no output schema and no annotations, the description covers purpose, provider, and return shape well enough to call it. The remaining gap is behavioral: latency, quota, and error semantics for a slow external API are unaddressed. That gap is small but real; I score it 4 rather than 3.

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 50%: url is documented ('URL to test'), while strategy has only an enum and a default. The phrase 'both mobile and desktop strategies' partly explains the strategy parameter, especially the 'both' default. It does not say what 'both' costs (two runs) or whether results are labeled per strategy.

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: 'Google PageSpeed Insights for a URL', and goes on to name concrete outputs (LCP, CLS, INP, score 0-100, opportunities). That is far more than a restated name. It loses a point because siblings check_pagespeed and check_performance look near-identical in intent, and the description never says how this tool differs from them.

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?

There is no when-to-use, when-not-to-use, or alternative guidance at all. With check_pagespeed and check_performance in the same family, an agent has no way to pick between three performance tools except by guessing. Usage is only implied by the phrase 'for a URL'.

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