crawl_stop

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

Goes well beyond the annotations: no billing for unfetched pages, in-flight pages still complete, no resume, idempotent behavior on an already-ended crawl, retry policy for 429/502/503/504 (3 retries, ≤50s total), the meaning of a 503 crawl_busy and CRAWL_BUSY, and the up-to-10-minute window where results keep growing.

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 action and the most decision-relevant facts (billing, no resume) before the operational details. Dense but nearly every sentence carries distinct information; the second paragraph is somewhat packed but not redundant.

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 still covers what a caller needs: final status on an idempotent call, billing behavior, retry/failure semantics, and the eventual-consistency window for results. Nothing material is missing for correct invocation.

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% for the single crawl_id parameter, and the description adds no syntax or format detail beyond it. Baseline 3 is appropriate when the schema fully documents the only parameter.

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 ('Stop a running crawl') and immediately scopes it: pages still waiting are not fetched or billed, in-flight pages finish. It distinguishes itself from the read-side siblings by pointing to crawl_results for the URLs already kept.

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?

Explains the context clearly: use it to halt a running crawl, then read retained output with crawl_results/crawl_get, and it cannot be resumed. It does not explicitly contrast against a hypothetical 'cancel' alternative, but the routing to crawl_results and crawl_get is unambiguous.

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