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

Annotations only say it is a non-readonly, idempotent, non-destructive, open-world call; the description adds substantive behavior beyond that: charges the prepaid balance, each item is drafted/proofed/final-quoted independently, results report queued or failed per item, retry-with-same-key resumes without double-sending, and 'queued' means not yet printed or mailed. That is exactly the kind of context 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?

Four short sentences, front-loaded with the core action and scale, then item composition, retry semantics, and the queued caveat in descending priority. No filler or repetition.

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 batch mutation with no output schema, the description covers cost source, per-item outcomes, retry behavior, and the queued-state caveat. It stops short of saying how to check batch progress afterward (the get_batch sibling exists), which would close the last loop for an agent.

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 low (33%), and the description compensates by explaining the two ways to populate an item (draft_id, or template_id + variables with recipient/sender) and the idempotency_key's retry semantics. It does not address content_policy_acknowledged, though the schema itself documents that field thoroughly, so the gap is minor.

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 verb, resource, and scale: 'Send up to 100 letters from the prepaid balance in one request.' The batch framing plus the prepaid-balance mention makes it immediately distinguishable from single-send siblings like send_with_credits, and the per-item composition is spelled out.

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?

Gives clear operational guidance: items can be built from draft_id or template_id + variables, and retries must reuse the same idempotency key and body to resume without double-sending. It does not explicitly name alternatives (e.g., single-letter send or quote-before-send siblings), so the routing is implied rather than stated.

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