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

Annotations only declare the mutation/open-world profile; the description adds substantial behavior: the job_id return contract, the required polling loop, the three finding buckets, the explicit non-measurement list, the no-invented-scores guarantee, and check-id traceability. This is exactly the operational context an agent needs to drive an async job and interpret results honestly.

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 short sentences, front-loaded with the action and the return contract before the follow-up workflow and scope caveats. Every sentence carries information, though the capitalization-heavy negative clauses read as a slightly disjointed list.

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 explaining returns and does so: job_id plus the grouping scheme for findings. Combined with the explicit non-scope list and the polling instruction, an agent has everything needed to invoke and consume 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 description never mentions 'url' or 'site_id', adding zero semantic detail beyond the schema. With only 50% schema coverage, site_id is completely undocumented in both places, and the required url's format constraints come solely from the schema. At mid coverage the description should have compensated and does not.

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+resource ('Start a full page audit') and immediately clarifies the async nature by noting it returns a job_id. The negative-scope sentence distinguishes it from rank/traffic/backlink tools that an agent might otherwise confuse it with, and the get_audit handoff separates it from the polling sibling.

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 a clear two-step workflow: start here, then poll with get_audit until status is complete, which is explicit routing to the correct alternative. It also enumerates what the tool does not cover, ruling out misselection. It does not compare against the site-level sibling crawl_site, so page-vs-site selection is left implicit.

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