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

With annotations only covering safety/idempotency flags, the description adds genuinely new behavioral context: asynchronous execution with an immediate job-id return, multi-minute latency, per-page billing, and that `limit` bounds page fetches. The authentication requirement is also disclosed. This is a strong disclosure layer over thin annotations.

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?

Three short, front-loaded statements with no filler: what it does, how it behaves asynchronously, and what it costs. The trailing auth line is terse but earns its place as a hard prerequisite.

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?

An output schema exists, so return values need no prose, and the async workflow, billing, and auth are covered. The remaining gap is the crawl-scoping model (depth, include/exclude paths), which the description never touches and which the schema does not explain either.

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 0%, so the description must carry all five parameters; it only explains `limit` (and does so usefully, tying it to billing). `url`, `maxDepth`, `excludePaths`, and `includePaths` receive no semantic explanation anywhere, leaving the depth and path-filtering model entirely opaque.

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?

"Start crawling a website" gives a specific verb and resource, and the description situates the tool precisely in the crawl workflow by naming `crawlStatus` and `crawlPages` as the follow-up steps. It stops short of differentiating itself from true alternatives in the sibling set such as `scrape`, `batchScrape`, or `map`, which an agent might equally consider.

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 description tells the agent the operational context well: it runs in the background, returns a job id immediately, and must be followed by `crawlStatus` and `crawlPages`. The prerequisite (a free SnoopScan key) is stated. It offers no explicit when-not-to-use guidance or routing away from sibling tools that also fetch pages.

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