voidmail_send_once

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

Goes well beyond the annotations: names the enforcement error codes (RECIPIENT_NOT_AUTHORIZED, CONTENT_CONTAINS_CREDENTIAL), guarantees 'Nothing is sent in either case,' explains the replay semantics (same ID + exact content returns original status; different payload conflicts), and warns 'Acceptance is not delivery.' None of this is derivable from readOnly/idempotent/openWorld hints.

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?

Front-loaded with the preferred-use verdict, then tightly sequenced into constraints, error behavior, idempotency semantics, and the fallback tool. Dense but every sentence carries operational information; nothing is decorative.

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?

A mutation tool with no output schema and only 17% schema coverage, but the description closes the gaps that matter: failure modes, non-send guarantees, replay/conflict behavior, and the escalation path. An agent can call this correctly without further context, aside from field-format details.

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 coverage is only 17% (just operationId documented), so the description must carry the load. It adds real meaning for operationId (host-persisted, never regenerated), for `to` (recipient policy enforcement) and for content fields (credential screening), but says nothing about subject/html/text/replyTo formats or precedence.

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 action (send exactly one message) with a distinctive mechanism: 'one message bound to a stable operation ID saved by the host before this call.' The phrase 'Preferred send' implicitly positions it against the sibling voidmail_send_email, and the idempotent-by-operationId framing separates it from a plain send.

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?

Explicit guidance for the ambiguous case: 'On uncertainty, use voidmail_send_status; never create a replacement ID automatically.' It names the alternative tool and states the prohibition, and 'Preferred send' signals this is the default choice over voidmail_send_email.

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