Retry webhook delivery

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description usefully explains why: it mutates the delivery by resetting its send time and retry counter. The asynchronous behavior (queue now, cron sends later) is genuine context beyond the annotations. It stops short of noting permission requirements or whether the reset affects other queued deliveries.

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?

Two tight sentences, no filler. The action and its effect come first, and the async caveat follows, so the agent gets the critical information without scanning.

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 an output schema present and annotations covering the safety profile, the description only needs to explain the queue-vs-send semantics, which it does. Adding whether the retry counter reset is bounded or whether permissions are required would make it fully complete for this mutation.

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%, so the single required parameter is already documented as 'QueuedWebhook ID'. The description adds no format, id-range, or lookup guidance for deliveryId. Baseline 3 applies when the schema carries the parameter documentation.

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 ('Queue a failed delivery for another attempt') with the exact mechanism (resetting send time and retry counter). It is unmistakable next to siblings like glpi_list_webhook_deliveries or glpi_get_webhook, and explicitly rules out an expectation the agent might otherwise have (no immediate send).

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?

Scope is clear: use it on a failed delivery to re-queue it. It also preempts a wrong mental model by explaining the cron does the sending, so the agent does not hunt for an immediate-send tool. It does not, however, name any alternative or state preconditions (e.g., delivery must be in a failed state), so it falls short of explicit when/when-not guidance.

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