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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that output is a set of fixes and that the target is the draft/template rather than the live site, but says nothing about cost, limits, or what happens on a published page.

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 sentences, zero filler, scope stated first and the return content tacked on at the end where it belongs.

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, so the description carries the burden of return shape and only offers 'Returns fixes' — no structure, no scoring scale (a 'score' is promised but never characterized). For a multi-dimension audit tool that is a meaningful gap, though the annotations cover safety.

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% and the schema already documents the id/templateSlug mutual exclusion, the page_home default, and the url-path semantics of pageId under templateSlug. The description only signals the site-vs-template mode at a high level, so baseline 3 applies since 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?

The description gives a specific verb (audit/score) and resource (a page of the site's draft or a stock template), and enumerates the audited dimensions: meta, heading hierarchy, alt text, link text, content depth. The SEO-vs-accessibility split from audit_accessibility is inferable from the listed checks, though the sibling is never named.

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?

It implies the applicable scope — the site's draft, or a stock template instead of a site — but never states when to pick this over audit_accessibility or how to handle published pages. Usage is inferable rather than guided.

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