sas_execute

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds the useful specifics: writes outside WORK/CASUSER are permitted, the run is backgrounded, it is stoppable, and results are paged. It stops short of saying what permissions are needed or how far a destructive statement can reach.

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?

Two tight sentences, front-loaded with the action and its scope, with the sibling comparison second. Nothing is padded or redundant.

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?

Given a destructive, 13-parameter execution tool with no output schema and no parameter documentation anywhere, the description is too thin to guide correct invocation. It covers the safety-relevant scope of writes well but leaves the agent guessing about nearly every argument.

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?

Thirteen parameters with 0% schema description coverage, and the description explains none of them — not sql, language, connection, pushdown, max_rows, wait_ms, or run_id. The only faint signal is 'paging', which loosely gestures at max_rows but gives no format or default guidance.

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 ('Run one SAS statement') and scopes it to statements the user confirmed in the SQL Editor, while noting that writes outside WORK/CASUSER are included. This differentiates it from a read-oriented sibling like sas_query, though the distinction is implied rather than spelled out.

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?

Embeds a real precondition — the statement must already be user-confirmed in the SQL Editor — which tells the agent this is not a free-form execution path. It points to sas_query as the behavioral twin ('same background run, Stop and paging') but never says explicitly when to choose sas_query, sas_stop, or sql_editor_execute instead.

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