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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered without the description. What the description adds is genuinely useful: the state machine, an indication that results only materialize on completion, and a per-key authorization constraint. It does not say whether there are rate limits or how long completed results are retained, which matters for a polling tool.

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, zero padding, with the state enumeration front-loaded and the access restriction placed last as a caveat. Every clause carries information an agent can act on.

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?

For a one-parameter read tool with full annotation coverage and an output schema, the description supplies what structured fields cannot: the status values and the key-scoping rule. A note on polling cadence or result retention would close the remaining gap.

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% and the single job_id property already documents its origin ("The job_id from start_crawl"), so the description adds no new meaning about the parameter. Baseline 3 is appropriate when the schema does the work.

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?

"Get a site crawl's status" gives a specific verb and resource, and the enumeration of queued/running/completed/failed makes the lifecycle scope unambiguous. It stops short of naming how it differs from the look-alike siblings (crawl_site, start_crawl), so an agent must infer that this is the read side of the start_crawl job rather than the thing that launches a crawl.

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?

The state list plus "pages_done counts up" makes the polling use case clear, and "Only the key that started a crawl can read it" is a real prerequisite that prevents a wasted call. There is no explicit when-not guidance or named alternative for retrieving completed crawl data by another route.

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