Run one engagement

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

The description extensively discloses behavior beyond the readOnlyHint annotation: determinism ('same seed always replays the identical engagement'), STALEMATE outcomes and the packages_expended reason, tactical-mode output differences, and the crucial flag that the data is 'Notional data.' No contradiction with readOnlyHint exists — the deterministic run-and-return semantics are consistent with a read-only computation.

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 a single dense paragraph with the core action front-loaded ('Run a single deterministic force-on-force engagement to completion') followed by the return-record enumeration. It runs long due to the output list, but every clause earns its place given there is no output schema to carry that information.

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?

With no output schema present, the description's detailed enumeration of the return record (winner, reason, duration, phase timeline, CEP breakdown, LOB/intercept counts, timestamps, end states, event log, and tactical-mode additions) serves as the de facto output documentation. Combined with the rich input schema (featured seeds, mode semantics, config defaults), an agent has everything needed to invoke and interpret the result.

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 description coverage is 100%, so the schema already documents mode, seed, and every nested config_overrides field with units, defaults, and ranges. The description adds only marginal parameter context, e.g., that tactical mode adds objective and sortie-tally outputs. Baseline 3 is appropriate when the schema carries the parameter documentation burden.

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 a single deterministic force-on-force engagement to completion' and enumerates the full return record. The 'single' qualifier distinguishes it from the sibling sweep_seeds, and the output enumeration (winner/STALEMATE, phase timeline, CEP breakdown, event log) leaves no ambiguity about scope.

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?

Provides clear context on what the tool does and how orbit/tactical modes alter behavior, which informs when an agent would call it. However, it never explicitly names alternatives or exclusion conditions — it doesn't say to use sweep_seeds for multi-seed exploration or compare_configs for configuration comparisons. Differentiation from sweep_seeds is only implicit in the word 'single'.

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