sas_stop

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

The description says the job's state is set to canceled and the session's running action is cancelled, which is a state mutation, while annotations declare readOnlyHint=true. Despite rich, useful detail (Compute vs CAS semantics, session survives, run ends "stopped" with the log so far), the description contradicts the annotation, and an agent trusting readOnlyHint would misjudge the side effects.

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?

Four tight sentences, front-loaded with the action and followed by the branch-specific behaviors and a pointer to sas_run_status. No filler; the parenthetical platform detail is dense but earns its place.

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 single-parameter control tool with no output schema, this covers the outcome state, platform-specific semantics, and where to read the log afterwards. Missing only how to obtain the run_id and whether any permission or ownership constraint applies.

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?

The schema has zero description coverage on run_id, so the description carries the burden; it never defines the identifier directly. It does, however, connect the run to its outcome and to sas_run_status, giving the agent enough context to know what run is being referenced and how to see its result.

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?

"Stop a SAS run from the SQL Editor" gives a specific verb and resource and scopes the origin surface. It does not explicitly distinguish itself from near-neighbors such as sql_editor_stop, stop_pipeline or workload_stop, so an agent must infer that this one is SAS-specific, but the SAS/Viya vocabulary makes the intent 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 implies usage through the waiting-run vs running-run distinction, which tells an agent this is the right lever for both queued and active runs. It never states when NOT to use it or names an alternative for stopping non-SAS work, leaving sibling selection to inference.

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