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

Annotations already declare it is a non-read-only, non-idempotent, open-world write, and the description adds the traits that matter operationally: the audit is asynchronous/background, it is rate-limited to one per day, and it does not return the score itself. These are precisely the behaviors an agent must account for and they are not derivable from the annotations.

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 sentences, front-loaded with the action and the rate limit, followed by the required follow-up call. Every clause earns its place with no redundant restatement of the title.

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 not be described here; the description instead covers the async nature, the daily cap, and the polling step needed to observe the result. That is everything required to invoke and use this tool correctly.

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 tool takes zero parameters, so the baseline is 4; there is nothing for the description to clarify beyond confirming it acts on the whole store. No misleading parameter implications are introduced.

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 (Queue/fresh audit) and resource (SEO audit of the whole store), clearly distinct from the read-oriented siblings like get_seo_summary and get_page_seo. An agent knows immediately this is the action that initiates an audit rather than retrieving one.

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 context (whole-store audit), an exclusion/limit (the same one-per-day cap as the in-app button), and routes the agent to the correct follow-up tool (get_seo_summary a few minutes later) since results are not returned inline. Nothing is left to inference.

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