ncloud_nks_create_cluster

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

Annotations only declare destructiveHint=false, so the description carries the full disclosure burden and does so well: it names the exact 400-failure conditions (missing lbPrivateSubnetNo, missing zoneCode, audit without CLA, regional zone/subnet mismatch) and the hard immutability of authType=API. These are failure-mode and side-effect details the agent could not infer from the single annotation.

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 action sentence, then cleanly sectioned into G3 requirements, new validations, and G2-vs-G3 differences; for a 24-parameter nested tool the length is justified. There is some verbatim overlap with the schema descriptions (e.g., the softwareCode pipe warning), which is minor redundancy rather than noise.

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 complex mutating create with nested nodePool/fabricCluster objects and no output schema, the description covers prerequisites, required-field pitfalls, and follow-up actions thoroughly. It does not describe the creation response or how to poll/confirm the resulting cluster (e.g., an operation handle), which is the main remaining gap given no output schema exists to cover return values.

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 already 100%, so the baseline is 3; the description earns above that by consolidating cross-parameter constraints (clusterType/k8sVersion/hypervisorCode coupling for G3, full-pipe softwareCode value) and by pointing at the sibling tools that supply each value (ncloud_nks_get_server_images, ncloud_nks_get_versions, ncloud_nks_get_server_specs). Much of the per-field detail nevertheless duplicates the schema, so it is not a 5.

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 first sentence states a specific verb and resource ('Create a new NKS Kubernetes cluster') and immediately scopes it with the dryRun preview option. This clearly separates it from adjacent tools such as ncloud_nks_create_node_pool, ncloud_nks_create_access_entry, ncloud_ses_create_cluster, and ncloud_cdss_create_cluster, which an agent can rule out from the name plus this sentence alone.

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?

It gives concrete when-to-use context: prefer dryRun=true to preview, check subnet zones before regional creation, subscribe to CLA before enabling log.audit, and install add-ons afterward with ncloud_nks_install_addons. It stops short of explicit when-not-to-use guidance (e.g., choosing SES/CDSS over NKS, or deferring node pools to ncloud_nks_create_node_pool), but the operational routing it does provide is specific.

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