Retrieve column metadata for a CAS table, including unloaded tables and database-backed caslibs, to inspect schema before querying or loading data.
Columns of a CAS table, loaded or not (for a database caslib CAS asks the database).
| Name | Required | Description | Default |
|---|---|---|---|
| table | Yes | ||
| caslib | Yes | ||
| connection | No |
Changes observed during successful MCP inspections.
v0.11.0Input schema / properties / connectionAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Connection"
+}v0.10.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so safety is covered. The description does add real context beyond that: it works whether or not the table is loaded, and for a database caslib the query is pushed to the database (a potential latency/connectivity implication). It does not say what a failure looks like or how large the result can be, so it stays at a solid but not rich 3.
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?
One short sentence with the resource front-loaded and the qualifier in a parenthetical — nothing wasted. The parenthetical is slightly compressed to the point of being cryptic ("CAS asks the database"), costing a point.
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 3-parameter tool with zero schema description coverage and no output schema, the description is too thin: it never defines connection, never indicates what a column entry contains (name, type, length), and never notes whether an unloaded-table lookup has side effects or cost.
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 0%, so the description carries the full burden, and it only supports 'table'/'caslib' implicitly through the phrase "CAS table." The third parameter, connection, is never mentioned and its role is left entirely undefined.
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?
"Columns of a CAS table" names the exact resource and scopes it to CAS tables, which distinguishes it from sas_columns and from the table-level siblings cas_tables/cas_caslibs. The verb is only implied (list/return), but the resource and scope are unambiguous.
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 never states when to pick this over sas_columns, sas_lookup_columns, or schema_explorer_preview, nor any precondition for calling it. The parenthetical about database caslibs is behavioral context, not usage routing, so the agent gets no guidance on alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.