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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains the async behavior, immediate envelope return with 'status: queued', polling requirement, plan allowance impact, Bearer token requirement, and quota/cooldown behavior—all substantive details.

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 informative, with the opening phrase front-loaded. The first sentence is dense with parentheticals, but all content is necessary for proper usage and expectations.

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?

Given no output schema, the description covers the async envelope, polling flow, included metrics, and key constraints (auth, quota, cooldowns). It lacks error-case details or a full response schema, but is adequate for an async 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?

The schema has one 'url' parameter with no description (coverage 0%), and the description does not explicitly define it, though it is implied as the audit target. It adds context about Google linking and per-domain cooldowns that relate to the URL, but does not fully compensate for missing parameter documentation.

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 clearly states the action with 'Queue a full SEO + AI-readability audit' and specifies the resource. It distinguishes from siblings by noting the inclusion of Core Web Vitals and organic traffic (if Google is linked) and requiring an API key, setting it apart from run_audit_anonymous.

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 provides explicit instructions to poll get_audit with the returned audit_id until status is complete, and notes the typical duration. It implies when not to use (if you lack an API key or want to avoid quota) by mentioning the anonymous sibling, though it does not explicitly name it.

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