List deliveries

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds non-obvious behavior on top: results are ordered newest first and records are pruned after 30 days. It does not say whether attempts are paginated beyond the limit cap or how failures are surfaced, but the retention and ordering facts are real added value.

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 tight sentences: what it returns and in what order, when to use it, and a retention caveat. The identifying information and the field list are front-loaded with no filler.

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 compensates by enumerating the return fields (eventId, attempt, status, httpStatus, error, durationMs, at, changeTypes), and it adds ordering and retention. For a two-parameter read tool with readOnlyHint set, nothing an agent needs in order to call it correctly is missing.

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 100%, with both the subscription id format and the 1–100 limit bound (default 25) fully documented in the schema. The description only reinforces the subscription scoping and adds nothing about the limit parameter, so this is the baseline case where the schema does the work.

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 ('Recent webhook delivery attempts for a subscription') plus ordering and the exact fields returned, which is far more than a restatement of the name. It never names a sibling like list_events, so the reader must infer the deliveries-vs-events distinction rather than being told it explicitly.

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 concrete triggering scenario: 'Use it to debug a receiver that is not getting webhooks or is answering with errors.' That is clear when-to-use guidance, but no alternative tool is named for adjacent tasks (e.g. checking whether an event was even emitted).

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