Skip to main content
Glama

Compare two rosters in combat

compare_rosters
Read-onlyIdempotent

Runs 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

NameRequiredDescriptionDefault
phasesNoPhases to return; defaults to all three.
rankByNoThe measure best targets and best attackers are ranked by.expectedWoundsLost
attackerYesThe attacking roster, in the shape save_roster and check_roster take.
defenderYesThe defending roster, in the same shape.
measuresNoNumbers each pairing holds, in this order; defaults to all three.
llm_modelNoThe 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_idNoThe 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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / attacker / properties / name / description
      Added value: +"The roster title, or empty to have one generated from the army and kept current. Send a name only when the player chooses one."
    • addedInput schema / properties / defender / properties / name / description
      Added value: +"The roster title, or empty to have one generated from the army and kept current. Send a name only when the player chooses one."
  2. Changed10 schema fields changed
    • addedInput schema / properties / attacker / properties / picks / items / properties / choices / additionalProperties / anyOf
      Added value: +[
      +  {
      +    "maxLength": 64,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  {
      +    "const": "",
      +    "type": "string"
      +  }
      +]
    • removedInput schema / properties / attacker / properties / picks / items / properties / choices / additionalProperties / maxLength
      Removed value: -64
    • removedInput schema / properties / attacker / properties / picks / items / properties / choices / additionalProperties / minLength
      Removed value: -1
    • removedInput schema / properties / attacker / properties / picks / items / properties / choices / additionalProperties / type
      Removed value: -"string"
    • changedInput schema / properties / attacker / properties / picks / items / properties / choices / description
      Previous value: -"One option per choice group, choice key to option id from get_unit_options, for groups it sets with choices: wargear, an enhancement, a detachment upgrade. Omitted groups keep their default."New value: +"One option per choice group, choice key to option id from get_unit_options, for groups it sets with choices: wargear, an enhancement, a detachment upgrade. Omitted groups keep their default; '' leaves an optional group empty."
    • addedInput schema / properties / defender / properties / picks / items / properties / choices / additionalProperties / anyOf
      Added value: +[
      +  {
      +    "maxLength": 64,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  {
      +    "const": "",
      +    "type": "string"
      +  }
      +]
    • removedInput schema / properties / defender / properties / picks / items / properties / choices / additionalProperties / maxLength
      Removed value: -64
    • removedInput schema / properties / defender / properties / picks / items / properties / choices / additionalProperties / minLength
      Removed value: -1
    • removedInput schema / properties / defender / properties / picks / items / properties / choices / additionalProperties / type
      Removed value: -"string"
    • changedInput schema / properties / defender / properties / picks / items / properties / choices / description
      Previous value: -"One option per choice group, choice key to option id from get_unit_options, for groups it sets with choices: wargear, an enhancement, a detachment upgrade. Omitted groups keep their default."New value: +"One option per choice group, choice key to option id from get_unit_options, for groups it sets with choices: wargear, an enhancement, a detachment upgrade. Omitted groups keep their default; '' leaves an optional group empty."
  3. Changed2 schema fields changed
    • addedInput schema / properties / conversation_id
      Added value: +{
      +  "description": "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.",
      +  "type": "string"
      +}
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "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.",
      +  "type": "string"
      +}
  4. Changed2 schema fields changed
    • changedInput schema / properties / attacker / properties / disposition / description
      Previous value: -"Force disposition id from get_unit_options' roster.dispositions; null when the detachment allows only one."New value: +"Force disposition id from get_unit_options' roster.dispositions, or null to leave the choice to each battle."
    • changedInput schema / properties / defender / properties / disposition / description
      Previous value: -"Force disposition id from get_unit_options' roster.dispositions; null when the detachment allows only one."New value: +"Force disposition id from get_unit_options' roster.dispositions, or null to leave the choice to each battle."
  5. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial behavior beyond that: full-strength starting state, per-target weapon choice, partial-status semantics with stoppedBy, the 30-second cutoff and the one-to-two-second expectation for 2,000-point lists. The main gap is that it never says what happens with oversized or invalid rosters, but the timeout and partial-result behavior are exactly the kind of context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and the simulate_combat comparison, and nearly every sentence carries operational information rather than filler. It is dense to the point of being hard to parse in places — the bestTargetOf/bestAttackerOf sentence is a long run-on — which costs it a point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the full return-value burden and does so: phase-indexed cells[attacker][defender], null for uncalculated pairings, notCalculated grouped by phase and reason, bestTargetOf/bestAttackerOf semantics including the ignore-uncalculated and empty-when-unfinished rules. Combined with the timing and partial-status notes, an agent has everything needed to interpret the result correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3; measures order and rankBy are already documented in the schema and the description only restates that cells follow measures order. The sentence about 'attackers and defenders list the units in roster order, entries giving their 1-based roster entries' is also loosely worded against a schema where those parameters are whole roster objects, adding little usable meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — runs every unit of one roster against every unit of another in the exact combat simulator — and explicitly frames itself as the whole-roster table equivalent of simulate_combat. The sibling differentiation is built into the first sentence, so an agent can tell it apart from simulate_combat without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternative: one call instead of a simulate_combat call per pairing, and closes by routing to simulate_combat when the agent needs to drill into a single pairing with chosen rules, modifiers or losses. It also states the default-conditions scope (passive rules on; stratagems, conditional rules, cover and range bonuses off), which tells the agent when this tool's numbers are and are not the right ones.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources