casino_results

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It explains that values come from CASINO-printed data, that missing values return null with a reason, that running DMC results are read from dmc.status, that dmc.status is deleted on completion, and that casino_stop preserves the last estimate. This is rich, non-obvious behavioral context.

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 long but information-dense, with each paragraph covering a distinct behavioral area: output contents, phase semantics, running jobs, and equilibration. The structure is front-loaded with purpose and then deepens into edge cases. The awkward opening phrase 'Physics out of a job's files' slightly reduces clarity but does not waste space.

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 that an output schema exists and the tool has only one parameter, the description is unusually complete. It covers completed runs, running DMC runs, stopped runs, equilibration, value provenance, and the meaning of `result`. An agent has enough context to invoke the tool correctly and interpret its results in most scenarios.

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 input schema has one required parameter, job_id, with 0% schema description coverage, and the tool description never mentions job_id explicitly. It refers to 'a job's files' and 'this run,' but it does not explain how job_id selects the job, where to obtain valid job IDs, or any constraints. Because schema coverage is low, the description was expected to compensate and did not.

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 states that the tool reads a job's `out` file and returns energies, error bars, variance, per-block numbers, and phases, which clearly identifies it as a results-reading tool. It also explains the `result` field as the run's answer, giving concrete purpose. It does not explicitly name sibling distinctions, but the resource and operations are clear.

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 provides useful conditions for when this tool is appropriate, especially for running DMC runs, saying it is 'the only way to read one.' It also covers stopped runs and equilibration states. However, it never explicitly contrasts the tool with casino_status or casino_list_jobs, so alternative routing is only implied rather than stated.

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