ncloud_datacatalog_update_table_schema

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

The description adds substantial behavior beyond the idempotentHint/destructiveHint annotations: it discloses the full-replacement (not merge) semantics, warns with ⚠️ that omitted columns are removed, and frames the corrective use case. The destructiveHint=false annotation is not contradicted — removal is at the schema/metadata level, and the description is what makes that side effect explicit to the agent.

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 sentences, each earning its place: the core semantics with a front-loaded ⚠️ warning, the when-to-use rationale, and the actionable read-first instruction naming the sibling tool. No wasted words and the critical safety warning is right at the start.

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 4-parameter mutate tool with no output schema, the description covers the operation semantics, the critical gotcha (schema replacement removes omitted columns), the trigger condition, and the prerequisite read step. The only minor gap is no statement about success response or whether partition keys/properties are affected, but with no output schema and a simple contract, this is not a material omission.

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%, so the baseline is 3. The description earns a 4 by reinforcing the semantics of the `columns` parameter — that the given list is the complete replacement and order/omission matters — which ties directly to the schema's 'Full replacement column list, in the desired column order' note. The identifier parameters (catalogId, databaseName, tableName) are self-evident and already documented.

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 ('Replaces'), a precise resource ('the table's ENTIRE column schema'), and the distinctive all-or-nothing behavior ('columns not included are removed'). This clearly differentiates it from the read-only sibling ncloud_datacatalog_get_table_schema and other datacatalog tools.

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 names the exclusive use case ('This is the only way to correct a column type a scanner inferred wrongly') and gives an explicit precondition with a named sibling tool ('Read the current schema first with ncloud_datacatalog_get_table_schema'). An agent knows exactly when to invoke it and what to do beforehand to avoid clobbering columns.

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