Re-queue a dead-lettered delivery

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

Annotations only say readOnlyHint=false and openWorldHint=true; the description adds the concrete gating rule that nothing executes without confirm: true and that no server-side dry run exists, which is genuinely useful pre-call context. It still doesn't say what retrying does to attempt counters, rate limits, or whether the delivery can be retried more than once.

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 sentences with zero filler: purpose plus endpoint first, then the write-gate constraint. Nothing redundant or buried.

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?

For a mutation with no output schema, the description covers the execution gate but not the outcome — what a successful retry returns or what state the delivery moves into. It also leaves undefined what qualifies as 'dead-lettered' and how an agent obtains a valid id.

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 67% and already documents both `confirm` and `idempotencyKey` inline, including the preview-on-omit behavior. The description's only added nuance is 'no server-side dry run,' which clarifies that the preview is client-side, so it adds marginal meaning beyond the schema.

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?

Names a specific verb and resource ('Re-queue a dead-lettered delivery') and pins it to the exact endpoint POST /v1/notification-deliveries/{id}/retry. That is clearly distinguishable from sibling read tools like notifications_listDeliveries.

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 phrase 'dead-lettered delivery' scopes usage to failed deliveries awaiting retry, which implicitly excludes healthy deliveries or listing operations. It stops short of explicitly naming the sibling used to find a dead-lettered id (notifications_listDeliveries) or stating when not to retry.

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