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

Goes well beyond the readOnlyHint annotation: discloses the 2,000-job retention window, that attempt_log keeps only the newest 10 attempts captured at send time, that only url_host is exposed (never the full URL), the exact status vocabulary, and that the call is free. Pagination termination (next_cursor null) is spelled out.

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?

Dense and front-loaded — the resource, ordering, and event scope come first, then record fields, then pagination and retention limits. It is a single long block rather than segmented, but almost every clause carries operational information; little could be cut without loss.

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 fully carries the burden of describing the return shape: the per-delivery fields, attempt_log contents, pagination contract, and coverage ceiling. An agent can call this correctly and interpret results without opening any other source.

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, but the description adds meaning the schema lacks: page size default of 20, the 1–100 range, and the null-sentinel convention for next_cursor on the last page. The api_key parameter is left to its schema description.

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+resource (list webhook deliveries for your key) and immediately bounds it: newest job first, event types named (job.started, job.completed/failed, usage.threshold). It also equates itself to GET /api/v1/webhooks/deliveries, making the scope unmistakable versus siblings like get_webhook_events or redeliver_webhook.

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 makes the use case clear (inspecting what Roster sent or attempted, with status and attempt_log for debugging failures) and implies read-only retrieval. It does not explicitly name when to reach for a sibling instead — e.g. get_webhook_events for configuration or redeliver_webhook to retry a failed delivery — so routing 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.