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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new context beyond that: the notifications:manage permission requirement, the warning that receipts may contain destination signing secrets, and the caveat that receipt state is historical rather than current authority. These are the kinds of facts an agent cannot get from structured fields.

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, each carrying distinct content (what it does, permission/secret warning, state caveat), with the core action front-loaded. No filler, though it is dense enough that the secret warning and permission requirement sit in one run-on line.

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 single-parameter read tool with no output schema and rich annotations, the description covers the essentials an agent needs: authorization requirement, a sensitivity warning about the payload, and the interpretive caveat about historical state. It could still say something about receipt contents or the request_id source, but nothing critical is missing.

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?

There is one parameter with 0% schema description coverage, so the schema does not explain request_id at all. The description says 'exact original request receipt' but never clarifies what request_id refers to, where it comes from, or whether the receipt is keyed by request, delivery, or rule, 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 and resource ('Recover the exact original request receipt') and scopes it with 'without replaying or enabling delivery', which meaningfully separates it from sibling tools like get_attention_notification_delivery and retry_attention_notification_delivery. It doesn't name those siblings explicitly, so the differentiation is implied rather than stated, but the agent can still tell what the tool returns.

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?

'Without replaying or enabling delivery' implies the situations this tool is not for, and 'read current state afterwards' gives a follow-up step, which is useful workflow guidance. However, no alternative tool is named and no explicit condition for choosing this over get_attention_notification_delivery is given, leaving the routing to inference.

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