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

Beyond the annotations, the description discloses a rate limit (10 checks per minute) and the side effects of the call: found proof is recorded and reconciled, and absent proof sending remains paused. This explains why the tool is flagged as a mutation and as open-world (it reaches out to the mailbox or LinkedIn), which the annotations alone would not convey. It does not explain what is 'destructive' in the annotation, leaving that hint partly unexplained.

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?

Four short sentences, front-loaded with purpose, then side effects, then limits. The final sentence restates idempotentHint without adding new information, which is the only real redundancy.

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?

The description covers purpose, side effects, rate limiting, and idempotency, which is substantial for a mutation tool. However, with zero schema description coverage on two parameters (one a nested free-form object) and no output schema, it should say more about the messageId/body input and what a 'proof found' check returns in order to be fully callable without guesswork.

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% and the description adds no meaning about the messageId parameter or the nested body object beyond the phrasing 'the same input'. With a required UUID and an untyped additionalProperties body, the agent gains no information about what body is for or whether messageId alone suffices.

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?

The description states a specific verb (checks) and specific resources (sending mailbox, LinkedIn) for a well-scoped object: a message whose delivery is unknown. It clearly distinguishes this from simply reading a message status, though it does not name a sibling tool such as getMessageOutcome or getQueuedMessage to sharpen the boundary.

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 condition for use is explicit: only for messages with unknown delivery, where sending is currently paused awaiting proof. There are no stated exclusions or named alternatives for the adjacent read-only outcome tools, so the agent must infer that this is not a general status lookup.

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