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

Descriptions go beyond annotations by disclosing cost side effects and the two-step confirmation flow: 'Costs credits (price returned before any charge on the confirmation field)'. Also mentions the output structure (each finding names the page) and async behavior. No contradiction with readOnlyHint/destructiveHint.

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 concise sentences pack in when to run, what it does, what content it returns, cost/confirmation behavior, and async polling. Slightly long first sentence but remains readable and efficient without redundancy.

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 the side-effecting nature (cost, async), the description covers all critical usage context: timing, confirmation flow, cost, and polling method. Without an output schema, it hints at the return shape ('each finding names the page'). Could be more explicit about error handling or cancellation, but not necessary for a minimum-viable usage.

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?

Input schema already provides 100% documentation for all three parameters with clear descriptions. The description adds context about the confirmation flow and cost but does not add new parameter-specific semantics beyond what the schema already covers. Baseline of 3 is appropriate.

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 tool crawls a site and reports specific audit findings (broken links, missing titles, etc.), using an imperative verb and identifying the target resource. It also differentiates itself from siblings by noting the async pattern ('Async: poll with site_audit_get') and the timing ('Run right after deploying').

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?

Explicitly tells when to use ('right after deploying') and how to handle async flow, but does not explicitly state when *not* to use it or list alternative tools for contrast. The reference to 'site_audit_get' provides a helpful companion but falls short of a full alternatives comparison.

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