ncloud_sens_send_mail

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

Annotations are empty, so the description carries the full burden, and it delivers: HTTP 202 with requestId (async acceptance), migration context (unified API that replaced Cloud Outbound Mailer on 2026-09-17), and the dryRun=true preview-without-sending escape hatch. It omits auth requirements, rate limits, and cost implications of dispatching mail, but the core operational behavior of a mail-send tool is well disclosed.

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 sentences, front-loaded with the verb-resource pair, followed by endpoint, constraints, response contract, and the dry-run hint. Every sentence earns its place; there is 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 17-parameter tool with nested objects and no output schema, the description covers the critical decision paths, the response contract (202 + requestId), and the safe-preview path. Remaining details live in a fully described schema, so nothing needed to invoke the tool correctly is missing — though auth and quota behavior would round it out.

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 100%, so per-parameter meaning is fully handled by the schema — the baseline of 3 applies. The description adds value beyond the schema by encoding the conditional requirements (templateNo XOR direct content; recipients XOR recipientGroupFilter) that the schema cannot express, since it declares zero required fields.

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 through SENS Mail') and pins it to the exact endpoint (POST /mail/v2/services/{serviceId}/requests). The explicit SENS Mail channel plus the reference to the tracking sibling ncloud_sens_get_mail_request clearly separates it from send_sms, send_alimtalk, and send_brandmessage.

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?

Provides concrete operational guidance: the conditional parameter groupings (templateNo OR senderAddress/title/body; recipients OR recipientGroupFilter) and the dryRun preview switch — exactly the decision knowledge an agent needs. It names the follow-up tracking tool but does not explicitly state when to prefer this over sibling SENS channels, though the channel distinction is largely self-evident from the name.

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