Run a single deterministic force-on-force engagement to completion and return the full record: winner (or STALEMATE) with reason, duration, phase timeline, per-team fix quality (CEP breakdown), LOB and intercept counts per DF node, key event timestamps, drone/GCS end states, and the complete event log. Tactical mode adds the objective, sortie tallies and the per-airframe package state. Notional data.

Run count consecutive seeds (start_seed .. start_seed+count-1) under one configuration and return aggregate statistics only: win rates by team including STALEMATE, time-to-fix and time-to-kill distributions (mean/median/p10/p90), duration distribution, stalemate reasons, and notable seeds worth drilling into with run_engagement. Aggregation is computed server-side; per-run event logs are not returned. Max count 1000.

Run two CONFIG variants over the SAME consecutive seed range (a paired experimental design: terrain and emplacement luck cancel out, so a few hundred seeds resolve real effect differences) and return each variant's aggregate statistics, the paired outcome deltas, the seeds whose outcome flipped, and a plain-language summary generated from those numbers. Use it to test doctrine questions, e.g. what happens to win rates when OPFOR adopts EMCON discipline. Max count 500.

Return the modeling assumptions: DF measurement and bearing-error model, RF propagation, fix estimation and its quality gates, drone state machine, EMCON semantics, outcome definitions, and the known simplifications. Read this before drawing conclusions from simulation results — it states what the model can and cannot support.

Return every parameter accepted in config_overrides: path, unit, default, sane range, and description — plus the parameters that are deliberately not overridable and why. This is generated from the same table that validates tool inputs, so it cannot drift from actual behavior.