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

Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint, so the safety profile is covered and 'Read-only' merely echoes it. The description adds genuinely new context: the call is 'free' (a cost/quota signal not in structured fields) and it discloses the response contents since no output schema exists. It says nothing about latency, rate limits, or audit freshness.

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?

Four sentences, each doing distinct work: trigger, return contents, cost/safety, and the one parameter. The usage trigger is front-loaded ahead of the return description, so an agent can decide relevance on the first clause.

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 by enumerating the audit's sections. It omits any sense of output shape, size, or pagination for large sites, which is a minor gap for a site-wide audit tool.

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 parameter's own description already states the default-false behavior and the grouped-issues fallback. The description's 'Pass include_pages for the per-page detail' restates the schema nearly verbatim, adding only a mild hint that per-page detail is opt-in for drill-down. 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?

The description uses a clear verb-and-resource pairing ('Returns the site-wide audit') and enumerates the contents: issues by severity, score trend, page performance, links/authority, and search ranks. It does not explicitly contrast with adjacent siblings such as get_visibility or get_competitors, so an agent must infer the boundary between site SEO audit and visibility/competitor 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?

It gives an explicit trigger condition — 'when the user asks how to improve their SEO or what is holding their site back in Google' — plus a secondary trigger around standing orders, which is unusually concrete. It stops short of stating when-not to use it or naming a preferred alternative, leaving that to the agent.

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