ncloud_serverless_restore_cluster

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

With annotations completely empty, the description carries the full burden and does substantial work: it discloses that the call creates a new (billable) cluster, is asynchronous (202 Operation), does not support point-in-time restore, and can be safely previewed with dryRun. It omits that the agent should poll the returned operation, but the '202 Operation' marker at least signals asynchronous behavior.

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 dense sentences with no filler, and the core action is front-loaded before the conditional parameter logic. The length is justified by the tool's complexity (two mutually distinct source types plus exclusions), and every clause 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?

The tool is complex — 9 parameters, 7 required, deep nesting, no output schema, and no annotations — so the description carries a heavy burden. It covers the most critical call-time decisions (source-type requirements, no PITR, dryRun preview), but leaves gaps: the async polling flow after 202 is not explained, nor the cost/billing implication of restoring a cluster, which is material for an agent weighing whether dryRun is worth doing.

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 only 22%, so the description must compensate, and it does for the most error-prone part: the source object. The flat required array cannot express that originalClusterName is required only for BACKUP while adminUserName/adminPassword are required only for IMPORTED_BACKUP — only the description conveys this conditional relationship. It also sources backupName from a sibling tool. It does not explain unit/network/backupConfig/autoScale semantics, but the schema partially documents those.

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 specific verb+resource+mechanism: 'Create a NEW Cloud DB Serverless cluster from a backup,' and even provides the HTTP endpoint and expected 202 response. The 'NEW' emphatically distinguishes this restore-from-backup operation from the sibling ncloud_serverless_create_cluster, so an agent can disambiguate without opening the 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?

The description gives conditional field requirements per source.type (BACKUP needs originalClusterName + backupName; IMPORTED_BACKUP needs backupName + adminUserName + adminPassword), tells the agent where to fetch backup names (ncloud_serverless_list_backups), states an explicit exclusion ('No point-in-time restore'), and instructs the safe path ('Use dryRun=true to preview'). It falls short only of explicitly naming the alternative tool for green-field cluster creation.

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