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

Annotations declare a non-readonly, non-idempotent, destructive mutation, and the description adds substantial context beyond them: the action is queued for an immediate attempt with a fresh signature, then retried normally, and success is 'a request, not a promise' because the sender re-validates the rule and channel (off rule, disabled/deleted channel, paused channel all change the outcome). It also documents the return shape {id, status, result} and its enum values. Nothing here contradicts the annotations – the non-idempotent replay semantics are consistent with destructiveHint=true.

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?

Front-loaded with what it does, then sourcing the id, then semantics, then caveats and error cases – a sensible order. It is dense and slightly overlong in the final caveat clause, but no sentence is filler given the tool's subtle async semantics.

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?

Despite having no output schema, the description states the return fields and their meanings, plus the error conditions. Combined with a single-parameter schema, an agent has everything needed to call this correctly and interpret the result.

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% and the sole parameter is documented, so the baseline is 3; the description earns above that by adding validity constraints tied to that id – ownership, the 15-day age limit, and the `unsupported` channel/event mismatch – which the schema description does not state.

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 first sentence gives a specific verb+resource ('send ... alert deliveries again') and pins it to the underlying endpoint POST /v1/alerts/deliveries/{id}/resend, clarifying it covers webhook or e-mail deliveries that failed, expired, or were lost. This cleanly distinguishes it from alerts_events (which lists deliveries) and alerts_test_webhook (which tests a channel rather than replaying a real event).

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 routes the agent to alerts_events for the `id` and states the operating window ('works whatever the delivery's status, up to 15 days after its event'). It also names when-not cases (not the user's own, older than 15 days, `unsupported` status) that produce errors, so the agent can pre-check rather than guess.

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