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

With no annotations at all, the description carries the full burden and does meaningful work: it discloses the billing model (one credit per accepted recipient), the auth requirement, idempotency-based retry semantics, and the important caveat that acceptance is not proof of remote delivery. It stops short of saying what the response contains or whether partial recipient rejection is possible.

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?

Three short sentences, each carrying distinct information: cost, auth, retry/delivery semantics. Front-loaded with the action and the cost, with zero filler.

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 15-parameter, nested-object mutation tool with no annotations and no output schema, the description covers cost, auth, and idempotency well but omits the return shape entirely — an agent cannot tell whether it gets a message ID, a queued status, or a per-recipient outcome. That gap matters given the explicit warning that acceptance ≠ delivery.

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 33% across 15 parameters, so the description should compensate more than it does. It adds real meaning for idempotencyKey (reuse on retries) and ties recipient counts to credit cost, but the remaining bulk of parameters (to/cc/bcc limits, body selection, headers, attachments) is left entirely to the schema.

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?

"Submit mail" gives a concrete verb and resource, and the credit clause makes clear this is the actual send path rather than a draft. It never names the sibling propose_email, so an agent must infer the boundary between proposing and sending from sibling names alone.

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?

"with existing credits" and "Requires a Bearer API key" imply prerequisites (funded account, authenticated key), and "Reuse idempotencyKey for retries" scopes one specific workflow. There is no explicit when-to-use/when-not guidance and no mention of check_balance, check_sending_status, or propose_email as alternatives.

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