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

Annotations only say read-only and non-destructive; the description goes far past that by disclosing the status state machine (queued/running/done/failed), the polling interval, the 10-pages-per-call page size, the reportUrl retention of 30 days, error shapes for failed crawls, and that an unknown or expired job id is an error.

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?

The purpose is front-loaded and no sentence is filler, but the middle is a dense multi-clause run-on about status, paging and errors that takes a second pass to parse. Tightening the paging clause would cost nothing in completeness.

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?

There is no output schema, and the description compensates fully by describing the return envelope (summary, reportUrl, result), what result contains at each stage, and how errors are surfaced. Nothing needed to call it correctly is missing.

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%, so the baseline is 3, but the description adds real semantics the schema lacks: cursor comes from nextCursor, advances the page window by 10, and its null counterpart signals the last page. That is the meaning of the field, not just its type.

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 opens with a specific verb and resource ('Reads a crawl started by start_site_crawl'), which immediately ties it to the sibling that creates the job and marks it as the retrieval half of a two-tool pair.

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 explicit polling guidance ('call again in 20 to 30 seconds'), explicit pagination guidance ('pass nextCursor back as cursor for the next 10'), and the termination condition ('nextCursor is null on the last page'). The reader knows both when to call and how to keep calling.

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