pagespeed_audit

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and external-call behavior are covered. The description adds a genuinely useful prerequisite — it consumes PAGESPEED_API_KEY or CRUX_API_KEY when set — but says nothing about what happens without keys, rate limits, or how long the audit takes, which matters for a live external API call.

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?

A single dense sentence with no filler, front-loading the data returned and ending with the credential note. It is efficient, though the comma-list of outputs reads as a feature dump rather than a structured lead-in.

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 usefully enumerates the return payload, and it covers the API key prerequisite. However, for a 3-parameter external audit tool it omits parameter guidance and any hint about usage relative to the many sibling performance tools.

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 only 33%: only 'categories' is documented in the schema, while 'url' and 'strategy' carry no description. The description adds no parameter meaning at all — it never mentions strategy defaults, that url must be a publicly reachable page, or what happens when categories is null, so it fails to compensate for the coverage gap.

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?

The description enumerates what the tool returns (Lighthouse scores, lab metrics, opportunities by savings, failing SEO audits, field data), which makes the underlying action — run a PageSpeed Insights audit — easy to infer. It never states the verb explicitly and does not distinguish itself from siblings such as core_web_vitals or performance_overview, which also cover performance/field data.

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 guidance, no exclusions, and no named alternative. An agent choosing between pagespeed_audit, core_web_vitals, performance_query, and diagnose_url gets no routing help beyond the output list.

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