crawl_wait

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

Goes well beyond the readOnly/destructive annotations: it discloses the timeout-retry contract, the progressToken progress-notification behavior, and the subtle semantic that a completed crawl with no results and no error is not a failure. This is exactly the kind of edge-case behavior an agent cannot infer from structured fields.

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-loads purpose before routing, edge cases, retry, and progress details. Every sentence carries information, though the list of return fields and the parenthetical state enumeration make it slightly denser than strictly needed.

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 must convey return values and it does (status, counts, first_urls), plus timeout/retry behavior and progress notifications. Nothing an agent needs to call this tool 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% and the schema already documents both crawl_id and timeout (default 50, 60s client cancellation caveat). The description only alludes to timeout behavior via 'if the wait runs out first' and adds no parameter detail beyond the schema, so baseline 3 applies.

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 and resource ('Poll a crawl until it ends'), enumerates the terminal states (completed, stopped, failed), and names the return payload (status, counts, first_urls). It is clearly distinguishable from crawl_get, crawl_results, and crawl_download, which are explicitly referenced.

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 clear routing guidance: after results, call crawl_download for one file or crawl_results for pages; if the wait times out, call crawl_wait again. It also points to crawl_get for the completed-with-no-results case. It lacks an explicit 'do not use when you only want a one-shot status check' exclusion, so it falls just short of 5.

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