Send a reviewed draft email

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

Beyond the annotations (which only declare non-read-only, non-idempotent, open-world), the description discloses the MAILATTIC_SMTP_ENV_FILE configuration requirement and rich failure semantics: what status='partial' means, that accepted recipients still received the message, and that an error may not mean the mail was undelivered. This is exactly the extra behavioral context the annotations cannot carry, and nothing contradicts them.

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 action, then prerequisites, then hard safety constraints. Every sentence carries operational weight — env requirement, review/confirmation gate, partial-send rule, unknown-outcome rule — with no restatement of the name or 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 non-idempotent send operation with an output schema, the description covers the two things an agent most needs and the schema cannot express: the confirmation gate and the re-send failure modes. Return-value shape is left to the output schema, appropriately.

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 must compensate, and it does: it identifies draft_id as coming from the dedicated draft folder and the fingerprint as a SHA-256 value matching that draft, obtained from mail_draft_reply. That supplies provenance and a matching requirement not present in the bare schema, though it gives no format example or guidance on fingerprint mismatch.

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 opens with a specific verb+resource ('Send a reviewed draft') and narrows the scope to drafts in the MCP-dedicated draft folder, which distinguishes it from sibling tools like mail_draft_reply that create drafts rather than send them. An agent can identify the operation and its source object without opening the 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?

It states the explicit precondition for use ('only call this after the user has reviewed the draft and explicitly confirmed to send'), points to mail_draft_reply as the source of the required fingerprint, and gives clear when-not-to-call rules for partial sends ('never call mail_send again for the same draft') and unknown-outcome errors ('verify delivery status before sending again'). This is a full when/when-not/alternative routing.

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