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

The annotations already declare this as a non-readonly, non-idempotent, open-world mutation, so the bar is lower; the description still adds two things the annotations cannot: that the caller owns the operation ID for safe retries, and that a successful response means acceptance, not delivery. That second point is genuinely useful behavioral context for a send tool.

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?

Two sentences, zero filler, and the core action is front-loaded before the retry and delivery caveats. Every clause carries information an agent needs.

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 four-parameter send tool with no output schema, the description covers the action, the idempotency-key contract, and the meaning of success. It leaves the path to actually confirm delivery unstated, which the voidmail_send_status sibling presumably covers.

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 0%, so the description must carry the load for four required params. It adds real meaning for operationId ('caller-saved', i.e. caller-generated and persisted) and identifies text as plain-text-only, but says nothing about `to` or `subject` beyond what the schema names.

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 and resource ('Submit one plain-text message') and scopes it to a single send, which distinguishes it from voidmail_send_status and voidmail_sending_limits without naming them. It is clear, though it never explicitly contrasts itself with its siblings.

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?

'Never retry with a new ID after uncertainty' is a concrete invocation rule for the retry path, and 'acceptance is not delivery' hints that delivery must be verified elsewhere. However, it never names voidmail_send_status or any other tool as the way to confirm delivery, so the routing guidance is only implied.

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