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

Annotations already indicate a non-read-only, non-idempotent write, and the description adds useful lifecycle details: the returned watchId is a secret bearer token, pulls are paid, adds are free, and the watch expires after inactivity. This goes beyond the annotations, though it doesn't specify how long inactivity is or what happens to unused credits.

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 sentences, with the core action first, the token-handling warning second, and lifecycle/pricing last. The metaphors ('census', 'tollgate', 'identity refused') add color but are not strictly necessary; still, no sentence is wasted.

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 a 3-parameter tool with no output schema, the description covers the essential return value (watchId), the security requirement, and the next workflow step (pull_ai_crawler_watch). It doesn't describe error cases or the exact response shape, but an agent has enough context to call it correctly.

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?

With 100% schema description coverage, the baseline is 3. The description reinforces that credits are pre-bought for pulls and that URLs are registered, but it doesn't add meaningfully to the freshness parameter beyond what the schema already provides.

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?

The description uses a specific action ('Register a set of URLs and pre-buy pull credits') and clearly states the resource being watched (crawler access changes) and the output (a watchId). It distinguishes itself from pull_ai_crawler_watch by framing this as the registration step and that as the retrieval step.

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?

It explicitly names pull_ai_crawler_watch as the companion tool to use for pulling changes, and the watch/expiry/pricing language conveys an ongoing-monitoring context. It doesn't explicitly contrast with one-off check/triage siblings such as check_ai_crawler_access, so it is clear but not exhaustive.

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