ncloud_mailer_delete_addresses

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

The description goes beyond the annotations by explicitly warning '⚠️ Destructive' and detailing the confirm=true requirement to execute. It also discloses the legacy status, merge date, and deprecation timeline, providing context that the annotations (destructiveHint, idempotentHint) do not fully capture. This is strong behavioral disclosure.

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?

The description is compact given the amount of context it conveys: legacy status, replacement pointers, destructive warning, and the core action. It front-loads the legacy warning before the actual purpose, which is logical, and avoids unnecessary filler. While dense, every sentence earns its place.

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 legacy tool with a confirm flag, the description covers the essential operational details: what it does, when to use it, the destructive nature, and the confirmation requirement. It does not describe return values, but there is no output schema, and for a delete operation the agent mainly needs to know the target and the confirm step. The absence of a response description is acceptable.

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?

The schema covers all parameters (100% coverage), but the description adds meaningful guidance for the confirm parameter ('Set confirm=true to execute') and reinforces the scope of emailAddresses ('from every recipient group'). This goes beyond simply restating schema descriptions, though the region parameter is left to the schema. The added value for confirm makes it a step above baseline.

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 states a clear action: 'Remove specific email addresses from every recipient group' with the HTTP method and resource path. It also distinguishes itself as a legacy tool that is being replaced by SENS APIs, naming the specific alternatives (ncloud_sens_send_mail / ncloud_sens_list_mail_requests), so an agent can tell when this tool is appropriate versus its modern counterparts.

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?

The description explicitly states when to use it: 'available only to projects migrated from Cloud Outbound Mailer and only for ~12 months' and points to the replacement tools for new mail sending. It also warns about the destructive nature and the need to set confirm=true, giving clear operational guidance on prerequisites and execution.

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