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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description goes well beyond them: it names the required mcp:send permission, documents idempotency semantics to avoid duplicate sends, and specifies that the body is plain text only. The duplicate-send and reconciliation warnings are meaningful risk disclosures annotations cannot carry.

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?

Five tight sentences, front-loaded with the action, then prerequisites, then retry safety. No filler and every clause carries operational information.

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 destructive, open-world mutation with no output schema and 9 mostly undocumented parameters, the description covers confirmation flow, permissions, idempotency, and recovery from uncertain results. The notable remaining gap is that no field-level format or recipient-list syntax is given for the six required identifiers/addresses.

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% across 9 parameters, so the schema itself says nothing about what each field means. The description partially compensates by explaining mutationId and queuedAt (retry/idempotency keys) and the body's plain-text constraint, but leaves emailAccountId, to, cc, subject, draftId, and replyToMessageId entirely unexplained.

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 and resource ('Send email') and scopes the mechanism ('mcp:send capability'), which is unambiguous against draft-oriented siblings like create_draft and save_mail_draft. An agent can tell this performs an actual send rather than a draft mutation.

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?

Explicit preconditions (user confirmation of recipients and content must already be obtained) plus concrete retry rules: reuse mutationId, queuedAt, and the exact payload on retries, and reconcile an uncertain result in Sent before sending again. This is exactly the when/how guidance a send tool needs.

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