List Watch Deliveries

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

Beyond the readOnlyHint annotation, the description discloses retention (90 days), webhook-only logging, and the empty-list behavior for email-only watches. This materially shapes agent expectations about empty results despite the read-only safety signal.

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 sentences carry purpose, scope, constraints, and usage intent with no filler, and the most important scoping claim is front-loaded.

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 covers the essential return content (status code, error, attempt number), retention, and the empty case. It does not specify ordering or any additional response fields, so it is strong but not exhaustive.

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?

The schema already documents limit, and the description adds only implicit meaning for watch_id via 'for one watch.' It does not elaborate on limit or provide richer guidance for either parameter, so with 50% schema coverage the description does only partial compensation.

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 it is a per-attempt delivery log for one watch and enumerates its content (status code, error, attempt number), so an agent can distinguish it from list_watches and list_watch_changes. The webhook-only qualification further narrows the resource and behavior.

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?

Explicitly gives the intended use: 'debug a webhook that is not arriving,' and tells agents not to expect results for email-only watches. It does not name a specific alternative sibling, so it falls just short of full routing guidance.

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