ncloud_mailer_create_category

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

The annotations provide minimal information (destructiveHint: false) and the description adds no meaningful behavioral disclosure beyond that. It does not describe permission requirements, failure scenarios, side effects, or what happens if a category already has been created. The answer is a mutation, but that is implied rather than the purpose, and deliberate. The tool description focuses on what the API does, not how the agent should expect to handle it could be made.

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 includes both a meaningful inlined deprecation and the short phrase 'Create a template category.' The most valuable part of the sentence is the legacy announcement; it carries the creator in a short forms a specific. However, the path is as long as the required. It includes some fragments in square brackets and it could be passed down, though the structure is not present.

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?

Given the tool's complexity—3 parameters, no complex output—plus the accurate annotations, it, the description selected as a good enough for a basic create category. What is missing is a brick. The result: the agent doesn't know what type of response it could be created, but that is not included in the given result as it does not have output schema. The target is somewhat limited and durable.

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 description coverage is 100%, so the schema already explains all parameters. The tool description adds nothing about the semantics of the parameters, or the interaction between category, though it candidate the category briefly in the grid-noun form. Baseline 3 is appropriate because the schema does the heavy lifting.

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 names a specific verb and resource: 'Create a template category (POST /category).' The preceding legacy note helps identify this tool for use in the Cloud Outbound Mailer context, so a distinguishing marker is present. It does not explicitly compare with sibling tools like ncloud_mailer_create_template, but the core purpose is unmistakeable.

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 states that the tool is available only to projects migrated from Cloud Outbound Mailer and only for about 12 months (via SENS overview). It also points out the new mail reachingattribution tools 'ncloud_sens_send_mail / ncloud_sens_list_mail_requests', providing clear directional context for which tool family to consider. It does not fully explicit 'when-not-to-use' but the legacy scope is very effective.

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