Compare two rosters in combat
compare_rostersRuns every unit of one roster, with its attached units, against every unit of another in Praetorium's exact combat simulator, as the simulator's whole-roster table does: one call instead of a simulate_combat call per pairing. attackers and defenders list the units in roster order, entries giving their 1-based roster entries as check_roster numbers them. Each phase's cells[attacker][defender] holds the measures in the order measures names, or null when that pairing could not be calculated; notCalculated groups those by phase and reason. bestTargetOf[attacker] lists the defenders that attacker does most to, and bestAttackerOf[defender] the attackers that do most to that defender, by rankBy; each is judged alone, ignores pairings it could not calculate, and is empty while any pairing in its row or column is unfinished or nothing does damage. Units start at full strength in default conditions: passive rules apply, while stratagems, conditional rules, cover and range bonuses stay off, and each weapon choice takes the option that does most against that target. A partial status means the table stopped early, as stoppedBy says; its finished pairings stand. Two 2,000-point lists take a second or two, and the table stops after 30 seconds. Drill into one pairing with simulate_combat to choose rules, modifiers or losses.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"attacker": "<attacker>",
"defender": "<defender>"
},
"name": "compare_rosters"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| phases | No | Phases to return; defaults to all three. | |
| rankBy | No | The measure best targets and best attackers are ranked by. | expectedWoundsLost |
| attacker | Yes | The attacking roster, in the shape save_roster and check_roster take. | |
| defender | Yes | The defending roster, in the same shape. | |
| measures | No | Numbers each pairing holds, in this order; defaults to all three. | |
| llm_model | No | The model identifier you are running as, for example "claude-opus-4-8" or "gpt-5.2". Pass "unknown" if you are not certain. Recorded for the server developer's analytics. | |
| conversation_id | No | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |