Skip to main content
Glama

Create a battle

create_battle
Destructive

Creates a battle in setup and returns its token. With nobody named it starts a draft with only you at the table, reusing your untouched draft with the same mission pack, and returns joinUrl: anyone with an account who opens it joins the open place, and the draft becomes a battle once every place is filled and every army chosen. opponentId seats one opponent from list_my_opponents for a duel; opponentIds seats one or two, and allyId seats a friend on your side, for a 2v1 or doubles. bothSides: true starts a duel you play alone instead: you hold both places and choose both armies from your own rosters, and it stays out of your record and the leaderboard. limit is the battle size in points (1000, 2000, 3000, or 600 for King of the Colosseum); omit it to take the size from the rosters, as a draft always does. missionPackId is a mission pack id from list_reference. casual: true plays it outside a tournament both players are entered in. manual: true tracks by hand without mission cards, stratagems or CP automation. groupToken counts it for a group both players are in, and fixture names that group's league fixture. Then set it up with submit_battle_action, following get_my_battle's next. Requires mcp:write.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_battle"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
allyIdNo
casualNo
manualNo
fixtureNo
bothSidesNoPlay every side yourself, choosing every army from your own rosters.
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.
groupTokenNo
opponentIdNo
opponentIdsNo
missionPackIdNo
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 / 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"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / bothSides
      Added value: +{
      +  "description": "Play every side yourself, choosing every army from your own rosters.",
      +  "type": "boolean"
      +}
  3. Changed1 schema field changed
    • removedInput schema / properties / guestNames
      Removed value: -{
      -  "items": {
      -    "maxLength": 48,
      -    "minLength": 1,
      -    "type": "string"
      -  },
      -  "maxItems": 2,
      -  "minItems": 1,
      -  "type": "array"
      -}
  4. Changed2 schema fields changed
    • removedInput schema / properties / clubToken
      Removed value: -{
      -  "maxLength": 64,
      -  "minLength": 1,
      -  "type": "string"
      -}
    • addedInput schema / properties / groupToken
      Added value: +{
      +  "maxLength": 64,
      +  "minLength": 1,
      +  "type": "string"
      +}
  5. Changed1 schema field changed
    • addedInput schema / properties / fixture
      Added value: +{
      +  "maxLength": 300,
      +  "type": "string"
      +}
  6. Changed1 schema field changed
    • addedInput schema / properties / clubToken
      Added value: +{
      +  "maxLength": 64,
      +  "minLength": 1,
      +  "type": "string"
      +}
  7. Changed1 schema field changed
    • addedInput schema / properties / guestNames
      Added value: +{
      +  "items": {
      +    "maxLength": 48,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "maxItems": 2,
      +  "minItems": 1,
      +  "type": "array"
      +}
  8. Changed1 schema field changed
    • addedInput schema / properties / manual
      Added value: +{
      +  "default": false,
      +  "type": "boolean"
      +}
  9. Changed4 schema fields changed
    • addedInput schema / properties / limit / anyOf
      Added value: +[
      +  {
      +    "maximum": 9007199254740991,
      +    "minimum": -9007199254740991,
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedInput schema / properties / limit / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / limit / minimum
      Removed value: --9007199254740991
    • removedInput schema / properties / limit / type
      Removed value: -"integer"
  10. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare write, destructive, non-idempotent and open-world; beyond that the description adds real behavior: it reuses an untouched draft with the same mission pack, returns a joinUrl whose holder joins the open place, the draft only becomes a battle when all places are filled and armies chosen, bothSides battles stay out of record and leaderboard, and mcp:write is required. It stops short of saying a repeated call creates a second battle or what happens to a reused draft that is later modified.

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?

Purpose and return value are front-loaded, and nearly every clause carries parameter meaning or mode logic. The single dense paragraph with semicolon-chained mode descriptions is harder to scan than a mode-per-sentence layout would be, but there is little wasted wording for 12 parameters.

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

Completeness4/5

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

For a 12-parameter, no-output-schema creation tool it covers the return values (token, joinUrl), the draft lifecycle, permissions, and the follow-up call. It leaves minor gaps: whether a named opponent is notified or auto-seated, what error occurs when a limit is incompatible with rosters, and how the returned token relates to get_my_battle identifiers.

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

Parameters5/5

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

Schema description coverage is only 25%, yet the description explains nearly every meaningful parameter: limit's values and the omit-to-derive-from-rosters behavior, opponentId vs opponentIds sizing, allyId semantics, bothSides side-ownership, missionPackId's source, casual and manual effects, and groupToken/fixture linkage. The two analytics parameters are self-documented in the schema, so the low coverage is fully compensated.

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?

The description opens with a specific verb and resource ('Creates a battle in setup and returns its token') and immediately distinguishes modes (draft, duel, 2v1/doubles, bothSides) that separate it from siblings like start_event_battle and submit_battle_action. An agent knows exactly what this creates and what it returns without opening the 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?

It routes the agent per intent: opponentId for a duel, opponentIds for 2v1/doubles, allyId for a friendly ally, bothSides for playing both sides, casual for outside tournaments, manual for cardless tracking, groupToken/fixture for group leagues. It also names list_my_opponents and list_reference as sources and hands off to submit_battle_action following get_my_battle's next.

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