Retry a dead or needs_review delivery with a fresh budget

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 critical safety fact that this is a WRITE which will not execute without confirm: true and that there is no server-side dry run, so the preview is purely client-side. It does not say whether requeue resets attempt counters, discards prior delivery state, or what permissions are required.

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, both load-bearing: the action and endpoint come first, the write-safety caveat second. No filler, no restatement of the title.

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 mutating retry endpoint with a nested body object, no output schema and a 50% documented schema, the description covers the essential decision points: what qualifies for requeue and the confirm gate. Gaps remain around post-requeue state (budget reset, idempotency on repeated calls) and error conditions.

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 50%, with confirm, idempotencyKey and acceptStale already documented inline. The description's confirm/write note largely restates the schema's own confirm description and adds no meaning for 'id', 'body', 'acceptStale' or idempotency behavior, so it only marginally compensates for the coverage gap.

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 (retry), a specific resource (a dead or needs_review delivery), and the effect (fresh budget), plus the underlying endpoint POST /v1/conversions/deliveries/{id}/requeue. The state qualifier 'dead or needs_review' distinguishes it from conversions_send and conversions_listDeliveries without opening either schema.

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 preconditions for use are explicit: the delivery must be in a dead or needs_review state. That is stronger than implied usage. However, it never names alternatives (e.g. re-sending via conversions_send, or notifications_retryDelivery for the notification-delivery domain) or states when not to requeue.

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