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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered; the description adds the meaningful extra context that a prior finished test must exist and that the response shape changes when auditId is supplied. It also discloses the secondary data source (xodia.seo.json) that supplies the searchEngines block, which the annotations cannot convey.

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, front-loaded with the core read semantics before the return-value and auditId detail. The middle sentence is dense with nested parentheticals and could be split for scanability, but no sentence is 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?

With no output schema, the description carries the burden of describing returns and does so concretely (scores, Core Web Vitals, top failed checks, searchEngines fields, full items for auditId). Only the behavior when no finished test exists at all is left unstated.

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 the baseline is 3, but the description adds real meaning beyond it: it explains the precedence between runId and the default latest run, names concrete sources for a runId (run_seo_test or a Fix with AI request), and gives auditId examples (image-alt, render-blocking-resources) plus what that parameter returns.

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?

Opens with a specific verb and resource ('Reads a PageSpeed Insights result') and immediately scopes it against the sibling that creates tests ('without using a test'), so an agent can tell this apart from run_seo_test without opening either schema. It also names the exact payload domain (scores, Core Web Vitals, failed checks, searchEngines).

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 clear selection rules: latest finished test by default, narrow by url, or target a specific runId, and says to pass auditId when one check's full detail is wanted. It implies rather than states that run_seo_test is the alternative when no finished test exists, so the exclusion is only implicit.

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