ncloud_cm2_request_advanced_certificate

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

Annotations only carry destructiveHint=false, so the description does the heavy lifting, and it delivers: main-account API key requirement with the specific failure mode (Sub Account keys rejected with HTTP 403), public-zone-only restriction, dryRun behavior, and the reuse semantics of persistent DNS validation. These are exactly the non-obvious operational traits an agent needs before calling.

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?

Front-loaded with the purpose, then layered constraints in short clauses; every sentence is actionable. The trailing provenance note ('confirmed by Ncloud support; verified 2026-10-02 with NCP_ADMINISTRATOR') is slightly verbose for the payload, but it justifies a claim an agent might otherwise distrust.

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 an 11-parameter mutation with no output schema and thin annotations, the description covers the critical failure modes, auth prerequisite, and validation-method choice. It does not indicate what a successful request returns (request token/handling state) or how keyAlgorithm/subscriptionPeriod affect the outcome, leaving a small gap an agent may need to discover at call time.

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% and the schema already documents every parameter, so the baseline is 3. The description still adds genuine meaning: the PD variant is clarified as 'set once, reused for later validations', and the OV/organizationNo dependency is restated as a hard requirement rather than a hint. That is a modest but real increment over the schema.

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 (request), a specific resource (paid Advanced DV/OV certificate) and the required input (a CSR), scoped to Certificate Manager 2.0. An agent can distinguish this from sibling request tools such as ncloud_cm2_request_cloud_basic_certificate or ncloud_cm2_request_global_edge_certificate without opening a 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 concrete conditions: organizationNo is required only for OV (NCP_PAID_OV_01), validationMethod D is one-time while PD is persistent, dryRun previews without requesting, and the target must be a public zone. It does not explicitly name the sibling tools to use instead (e.g. basic vs global-edge certificate), so routing is by inferred condition rather than explicit alternative.

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