casino_stop

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

With no annotations provided, the description carries the full burden and succeeds. It details that SIGTERM targets the job's casino processes, that runqmc survives to write output, that the current block is lost, and that haltqmc -f -u tidies the directory for resumption. It also explains the timeout fallback behavior.

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?

The description is front-loaded with the core purpose and then adds only high-signal behavioral details. Every sentence contributes meaningful operational knowledge without repetition or filler.

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 side-effect-heavy tool with no annotations, the description is remarkably complete: it covers signal behavior, persistence of completed data, loss of current block, directory cleanup, resumption path, and timeout semantics. An output schema is present, so explaining return values is not necessary.

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%, so the description must compensate. It fully explains timeout as the seconds a job gets before its process group is killed, but job_id is left to its schema title and the contextual phrase 'running calculation.' The main parameter is not explicitly defined or sourced.

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?

The description opens with a specific verb and resource: 'Stop a running calculation and leave its directory ready to be continued.' This clearly distinguishes casino_stop from the sibling tools casino_run, casino_prepare, casino_status, casino_results, and casino_list_jobs.

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 clearly establishes the tool's purpose for stopping a running calculation and contrasts it with haltqmc -k's account-wide behavior, implying this tool is job-scoped. It does not explicitly enumerate when to use it over siblings, but the intended use is unambiguous in context.

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