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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds real context beyond them: the data is *saved* rather than freshly gathered, focused sections can be read 'without running another audit', and get_seo_evidence can inspect deployed HTML while this cannot. It stops short of stating staleness windows or refresh semantics.

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 tight sentences, front-loaded with the primary capability, then the section routing tip, then the alternative-tool guidance. No filler and nothing repeated from the schema or annotations.

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?

An output schema exists, so return values need no elaboration. With purpose, sibling routing, the saved-vs-fresh distinction, and the noindex caveat all covered, an agent has everything needed to call this correctly rather than reaching for get_seo_evidence or run_audit.

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%, so the baseline is 3. The description adds selective meaning beyond the schema: section:'pageMetadata' enumerates what it returns (title, description, canonical, social-preview evidence), the default 'summary' is characterized, and 'full' is flagged as a last resort. That is more than the enum alone conveys.

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 ('Read saved performance causes, metrics, and page-metadata health') and immediately scopes the resource further with section:'pageMetadata'. An agent can distinguish it from get_seo_evidence without opening either 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 explicit routing rules: use section:'pageMetadata' for the audited page's saved metadata, but for fresh SEO / organic traffic / noindex questions start with get_seo_evidence instead. It also warns that empty performance recommendations do not establish SEO health, which is a genuine when-NOT-to-conclude rule.

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