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

Adds substantial behavior the annotations do not carry: the call is queued and returns before provider completion, completion must be polled via get_mail_action, and the retry policy is spelled out. Note a mild tension with idempotentHint=false — the operationId/retry wording implies deduplicated retries, though the annotation can be read as 'not idempotent without a key', so this is not a clear contradiction.

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 short sentences, purpose front-loaded, and every sentence conveys non-obvious operational information (async queueing, polling target, retry rule). No 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?

With no output schema, the description correctly explains the return shape (an immediate queued operation) and the follow-up call, which is exactly what this async tool needs. It omits details on body requirements/permissions and leaves senderIdentityId, to and subject unexplained, so it is strong but not fully complete.

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 only 11%, so the description carries most of the burden, yet it only explains operationId. High-value required parameters (accountId, to, subject) and optional ones (senderIdentityId, htmlBody vs textBody) get no semantic guidance in either place.

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 ('Create an unsent draft') plus scope ('in one connected mailbox'). The qualifier 'unsent' is what an agent needs to distinguish this from send_email, reply_to_email, and forward_email among the siblings without opening any 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?

Gives explicit operational rules: supply a stable operationId, reuse it only for retrying that exact draft, and poll get_mail_action with the returned operationId. It does not explicitly say when to prefer create_draft over send_email or reply_to_email, so it stops short of full when/when-not/alternative guidance.

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