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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered elsewhere. The description adds genuinely new behavioral context: expected latency of 20-90 seconds and the public-URL-only constraint, which explains why a call may be slow or rejected. It doesn't describe failure behavior beyond the address restriction, which keeps it short of 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?

Three sentences, each load-bearing: what it does, how long it takes, and what it will refuse. The capability and its return surface are front-loaded before the operational caveats, with no filler.

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?

There is no output schema, and the description compensates by enumerating the audit's returned dimensions in reasonable detail, so an agent knows what comes back. The remaining gap is minor: nothing is said about how failures or low-score results are surfaced, but the latency and eligibility constraints cover the practical essentials.

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%, so both the url and locale parameters are already documented in the schema. The description reinforces "public website" and pins the audit to mobile (a fixed, non-parameter choice worth knowing), but adds nothing about the locale parameter's effect on output language. Baseline 3 applies when the schema does the heavy lifting.

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 ("Runs a Google PageSpeed Insights audit of a public website on mobile") and then enumerates the exact dimensions returned: performance, accessibility, best-practices, SEO, Core Web Vitals, weighted issues, security headers and page weight. Nothing in the sibling set overlaps, and an agent knows precisely what capability it is invoking.

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 concrete runtime ("20 to 90 seconds") and a hard scope constraint ("Only public http(s) addresses"), which functions as an exclusion. There is no explicit when-not guidance, but the sibling tools (list_case_studies, request_contact, studio_info) are unrelated so no alternative routing is needed.

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