ncloud_datacatalog_create_scanner

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

The only annotation is destructiveHint=false; the description adds substantive behavioral context beyond it: creation is decoupled from scanning ('Creating a scanner does not scan'), a scan requires an explicit run or CRON schedule, and dryRun=true previews without persisting. These are non-obvious behavioral facts an agent needs. It doesn't contradict the annotation. It stops short of covering reversibility or permission requirements, so not a 5.

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 tight sentences with zero waste: the first defines purpose, the second clarifies the create-versus-scan lifecycle and names the sibling, the third covers the dryRun escape hatch. The most important distinction (create ≠ scan) is front-loaded second. No structured data is repeated.

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 19-parameter creation tool with no output schema, the description supplies the essential lifecycle context (create → run or schedule), names supporting tools (ncloud_datacatalog_run_scanner), and flags dryRun. The schema carries full parameter documentation. A minor gap is that the description never hints at what the call returns (e.g., scanner ID), which would help in the absence of an output schema.

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 100%, so the baseline is 3 — every parameter including the type-to-location/connectionId mapping is already documented in the schema. The description adds workflow-level context (dryRun, scheduleType=CRON, run_scanner) that reinforces parameter usage but doesn't convey meaning beyond what the schema's parameter descriptions already provide.

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 uses a specific verb and resource — 'Create a scanner that registers a data source as catalog tables' — and further specifies the exact purpose: exposing Object Storage, Iceberg, Cloud DB, and JDBC sources as queryable tables. It also distinguishes itself from the sibling ncloud_datacatalog_run_scanner by explicitly stating 'Creating a scanner does not scan,' so an agent can tell them apart without inspecting schemas.

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 explicit when-to-use context ('the standard path for exposing Object Storage or Iceberg data (and Cloud DB / JDBC sources) as queryable tables'), names an alternative (ncloud_datacatalog_run_scanner), and states the condition that selects it ('run it with ncloud_datacatalog_run_scanner (or set scheduleType=CRON)'). It also tells the agent dryRun can preview without creating. This is a complete routing story.

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