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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=true, openWorld=true), and the description adds real value beyond them: an authorization scope, an independent human-approval gate, the duplicate-acknowledgement contract, the 'cannot promise exactly once' delivery caveat, and the uncertainty/receipt reconciliation procedure.

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 sentences, front-loaded with the action and its required arguments, then prerequisites, then failure handling. Dense and efficient, with only minor compression possible around the deduplication clause.

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 tool with no output schema, the description covers authorization, approval, idempotency/dedup semantics, and post-call reconciliation. It leaves the identities of request_id and delivery_id unexplained, but otherwise an agent has enough to invoke it correctly.

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 0%, so the description must carry the load. It adds meaning for two of four params — expected_version as a concurrency guard and acknowledge_possible_duplicate as a mandatory true constant — but never explains request_id or delivery_id, so the schema-only parameters remain opaque.

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) and resource (attention notification delivery) with the distinguishing modifier 'eligible', and the description immediately names the required conjunction of expected_version and acknowledge_possible_duplicate=true, which separates it from the read/list siblings and from reconcile_attention_notification_delivery.

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?

Gives clear prerequisites ('Requires notifications:send plus independent human approval') and an explicit when-not-to-proceed rule: an uncertain response must be reconciled via its request receipt before further action, which routes the agent toward the reconcile sibling. It stops short of naming that sibling explicitly.

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