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

Goes well beyond the readOnly/openWorld annotations: async background execution returning jobId immediately, robots.txt compliance and inter-page pausing, minutes-scale latency for 50 pages, 24-hour result retention, and explicit exclusion of rankings, keyword volumes, backlinks and AI answer mentions. It also discloses what is logged (domain and path, never query string, IP or page text), which is material for an agent handling user URLs.

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 action and scope, then the polling contract, latency, retention and exclusions in a sensible order with no filler sentences. It runs long and the privacy/logging sentence is dense, but every clause carries decision-relevant information.

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 an async job tool with no output schema, the definition supplies the return contract (jobId), the polling cadence and terminal status, expected duration, retention window, and explicit out-of-scope checks. An agent can start the job, track it, and set user expectations without any further reference.

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; the description adds meaning by stressing "one site" and "up to 50 pages", which clarifies that pinned URLs must stay on the same domain and bounds the limit parameter. No further detail on url syntax is offered, but the schema already covers formats and ranges.

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 ("Starts a crawl of up to 50 pages of one site") and enumerates the exact problem classes it surfaces (broken links, duplicate titles, orphan pages, soft 404s). The phrase "the problems one page cannot show" implicitly carves it away from the single-page sibling check_page.

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 a clear activation condition ("Use it when the person wants the whole site checked") and a concrete follow-up loop: call get_site_crawl with the returned jobId every 20-30 seconds until status is done. It does not name check_page or request_full_audit as explicit alternatives, so the boundary with those siblings is inferred rather than stated.

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