Re-deliver an event

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

Beyond the annotations' safety profile, it discloses two behaviors an agent cannot get from structured fields: the payload and `X-PletoPay-Event-ID` are byte-identical on replay, and replays are throttled per business with a 429/`Retry-After` contract. These are exactly the traits needed to avoid hammering the endpoint or double-processing on the consumer side.

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, front-loaded with the verb and scope, then safety-relevant detail. Nothing is repeated from the title or the schema.

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?

There is no output schema, so the description is the only place behavior can be described; it covers scope, payload invariance, and throttling but never says what the call returns (delivery records? counts? nothing?). For a re-delivery trigger that gap is minor but real.

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 parameter docs already carry the basics (baseline 3). The description still adds meaning by making the semantics of omitting `endpoint` explicit — the fan-out is to every subscribed endpoint — which the schema's 'Only replay to this endpoint' 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?

States a specific verb and resource ('Re-deliver an event') and immediately defines scope: every subscribed endpoint or a single `endpoint`. That scope statement cleanly separates it from read-only siblings like get_event and list_event_deliveries.

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?

Clear about the operation's context and its consequences (dedup still applies, per-business replay limits), which implicitly tells the agent when a repeat delivery is safe. It does not explicitly contrast with the closest alternative, test_webhook_endpoint, so the agent must infer that testing vs. real re-delivery are different actions.

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