Check a crawl

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description goes well beyond them: it discloses that wait=true becomes a single held call bounded at ≤75s, that rows are returned inline when it converges, and it explicitly forbids loop-polling. Latency ceiling and retry semantics are exactly the traits annotations cannot express.

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?

Front-loaded with the core purpose, and the operational rule (never poll, use wait=true) lands early. Dense with em-dashes and parentheticals, and the phrase 'the answer to a crawl tool's 504 / crawl-id handle' takes a second read, but every clause carries information an agent needs.

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 does the work of naming what a non-wait status call returns and what an inline `data` payload is shaped by. It stops short of describing pagination or the exact envelope for the plain status case, which is a minor gap for a 6-parameter tool with a nested object.

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 description coverage is 100%, and the nested `output` object is documented in exhaustive detail in the schema itself, so the baseline is 3. The description adds real meaning on top: it ties `wait` to a held call and `data` shaping, and frames the return fields (counts, status, workflow id) that the schema cannot. It does not touch `limit`, `preview_chars`, or `timeout_seconds`, which is why it stays at 4 rather than 5.

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?

Names a specific verb+resource ('Status of a crawl by id') and enumerates what comes back (page counts, status, dataset workflow id). It also situates itself relative to the crawl-creating sibling by explaining it answers 'a crawl tool's 504 / crawl-id handle', so an agent can place it without opening the schema.

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?

Explicit and prescriptive: use wait=true rather than polling, and if the crawl is still running at the ceiling, re-call once the same way. It also states the condition for setting `output` (when the answer is for a program rather than for the agent to read). No inference required.

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