get_cluster_columns

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the platform limitation, the error condition on SQL Analytics Endpoints, and the empty-list result when no clustering columns exist, which gives the agent useful expectations beyond the raw operation.

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?

The description is compact and front-loaded, leading with the primary purpose and ordering behavior, then adding constraints and parameters. Every sentence contributes useful information with no filler.

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 description fully covers what the tool does, its supported platforms, failure behavior, edge case, and all parameter formats. Since an output schema exists, the return structure does not need to be explained in the description.

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 0%, but the description compensates fully by documenting all three parameters: workspace name or GUID, warehouse name or GUID, and a dot-separated qualified table name with an example. This adds real meaning that the bare input schema lacks.

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 and resource: 'Return the data-clustering columns of a table, ordered by clustering ordinal.' It clearly differs from siblings like get_table_columns or set_cluster_columns by focusing on clustering-column metadata and mentioning ordering behavior.

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 clear usage constraints: it is supported only on Fabric Data Warehouses and raises a ToolError on SQL Analytics Endpoints. It does not explicitly name alternatives, but this exclusion is strong enough to guide selection in most cases.

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