sas_lookup_columns

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

Annotations only declare readOnlyHint=true, so the description carries most of the burden and does well: it discloses that a nonexistent table returns ``missing: true`` rather than an error, which is genuinely non-obvious and changes how a caller handles results. It also discloses the batch limit of 8 and the per-language library namespace (SAS libraries vs caslibs). It says nothing about the connection parameter's role or any auth/session requirements.

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 short sentences, front-loaded with the verb, resource, and batch limit before the namespace and missing-table details. Some rst-style double-backtick markup and the parenthetical type notation add visual noise, but nothing is wasted.

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?

With no output schema, the description has to convey the return shape; it covers only the missing-table marker and says nothing about what a successful column payload looks like. Combined with the undocumented `connection` parameter, an agent can call it but cannot fully anticipate the response.

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% with three parameters, so the description must compensate. It documents `tables` as an array of {library, table} objects with an 8-element cap and implicitly reveals the `language` values (procsql, fedsql, cas) — solid value. The `connection` parameter is left completely undefined in both schema and description, leaving a real gap.

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?

States a specific verb and resource (lookup columns) plus an explicit scope: up to 8 tables in one call, for SQL Editor autocomplete. The library/table pairing and the procsql/fedsql-vs-cas namespace split further pin down what it returns, but it never names the close siblings (sas_columns, cas_columns, describe_table) that an agent might otherwise pick.

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 phrase "for the SQL Editor's autocomplete, in one call" implies bulk, autocomplete-oriented usage, and the 8-table cap signals batching rather than single-table inspection. There is no explicit when-not-to-use and no routing to the per-table alternatives, so the agent must infer the boundary from the batch size.

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