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

Annotations cover only the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description supplies the substantive behavioral context an agent actually needs: the Bearer credential requirement, the fact that the server cannot provision an inbox, the allowlist/guard precondition, and the crucial semantics that acceptance is not delivery and that retrying under a new ID after uncertainty is forbidden.

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?

Every clause is load-bearing: credentials, precondition, negative case, retry rule, delivery semantics. Preconditions are front-loaded and the two most dangerous operators (never retry with a new ID; acceptance != delivery) close the description where they will be read.

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 4-required-param mutation with no output schema and no annotation depth, the description covers auth, gating, retry, and delivery caveats thoroughly. The one omission is what the response actually contains and whether voidmail_send_status is the way to confirm outcome, which an agent would have to infer.

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 carries the full burden, and it only meaningfully explains operationId (caller-saved, must not be regenerated after an uncertain result). The other three required parameters (to, subject, text) are left to their names and JSON-schema constraints, so half the compensation job is undone.

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 precise verb+resource (submit one plain-text message) and immediately scopes it with the caller-saved operation ID. An agent can distinguish it from voidmail_send_status, voidmail_sending_limits, and the read-side voidmail_read_email without opening any schema.

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?

Explicitly states prerequisites (existing inbox agent key as Bearer; server cannot create an inbox), gating conditions (owner-set recipient allowlist with content guard on, approved recipients only), a when-not case (open inboxes are receive-only), and retry guidance. Nothing about when to use this versus alternatives is left to inference.

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