sas_lookup_columns

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

Goes beyond the readOnlyHint to disclose two meaningful behaviors: nonexistent tables return missing:true rather than erroring, and the batching cap of 8 tables. Both are decision-relevant facts an agent needs to plan calls, though return shape and per-table failure modes beyond 'missing' aren't covered.

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?

Dense but front-loaded: the batch size, element shape, and library-vs-caslib mapping appear first, with the missing-table behavior framed as the reason for the tool. No filler sentences, though the parenthetical RST code formatting is slightly noisy.

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 2-param read-only lookup with no output schema, the description supplies the essential call-shaping facts (batch cap, element shape, language-to-library mapping) plus non-obvious non-error semantics. A short note on the return payload's per-table keying would make it fully self-contained.

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% and both params are undocumented in the schema, so the description carries the burden. It explains the tables element shape as [{library, table}] and ties language to proc/fedsql vs. cas, which is genuinely necessary; but it omits valid language values and array length beyond the cap.

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+resource: retrieving columns for a batch of up to 8 SAS tables, scoped to the SQL Editor's autocomplete. Clear what it does, though it doesn't distinguish itself from sibling column-lookup tools like sas_columns and cas_columns beyond language/library context.

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?

Context is implied (SQL Editor autocomplete), and it hints at the 'remember briefly, don't ask again' caching behavior, but there is no explicit when-to-use vs. siblings like sas_columns or cas_columns. An agent could reasonably wonder whether to prefer those single-purpose tools.

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