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

Annotations already declare destructive=true, idempotent=true and openWorld=true, yet the description adds the auth prerequisite (verified sender) and, critically, the semantic limit of success: acceptance creates a durable request only, and pending_handoff must never be reported as sent or transport-accepted. That is exactly the kind of outcome-interpretation detail annotations cannot convey.

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?

Five short sentences, each carrying distinct information: action, precondition, scope limit, retry rule, and result semantics. The most failure-prone fact (pending_handoff is not a send) is placed last as a warning without padding elsewhere.

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 destructive, open-world mutation with no output schema, the description covers preconditions, idempotency and the meaning of the returned status, which is the hard part. It stops short of telling the agent what to do on a revision mismatch or how to follow up via get_ecard_status, leaving a small operational gap.

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?

With 0% schema description coverage, the description must carry the load, and it does: draft_id is tied to the exact reviewed revision, idempotency_key is tied to retry safety, and the sentence about non-replaceable fields clarifies what the call deliberately cannot change. expected_revision's role as a staleness/concurrency guard is only implied, not stated, so it falls short of full coverage.

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?

"Request dispatch of the exact reviewed draft revision" gives a specific verb (dispatch) and a precisely scoped resource (a reviewed draft revision), which separates it from prepare_ecard and publish_ecard. It never names a sibling outright, so an agent must infer that this is the send step rather than the compose step.

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?

Preconditions are stated clearly: a verified sender is required, and recipient, message and time cannot be substituted here, which tells the agent not to attempt a send-and-edit. Retry guidance for the idempotency key is explicit. What is missing is routing to alternatives, e.g. use prepare_ecard to change content or cancel_scheduled_ecard to abort.

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