Skip to main content
Glama

Read a Praetorium skill

get_skill
Read-onlyIdempotent

Returns step-by-step guidance for a task, including the Warhammer 40,000 knowledge and tool order it needs. Read the matching skill before starting the task. Skills: answer-a-rules-question: Answer a Warhammer 40,000 rules question from Praetorium's reference, citing the source. Use when someone asks how a rule, ability, stratagem, keyword, datasheet value or mission works. build-a-roster: Plan a Warhammer 40,000 army list from Praetorium's current units, points and detachments, weigh what each detachment gives a unit, and save the list to the player's Praetorium account when they ask. Use when someone wants to build, draft, improve, cost or save an army or roster, choose a detachment, or asks how a unit fits a list. choose-secondaries: Help a Warhammer 40,000 player choose between Tactical and Fixed secondary missions for a mission and opponent, from the secondary cards in Praetorium's reference. Use when someone asks which secondaries to take, or whether to go fixed or tactical. compare-units: Compare two Warhammer 40,000 units with Praetorium's combat simulator and explain the expected result. Use when someone asks how one unit does against another, which of two options hits harder, which wargear is best against a target, or what the odds are of destroying a target. explain-a-mission-matchup: Explain which primary missions, deployments and terrain two Warhammer 40,000 force dispositions get in a mission pack, from Praetorium. Use when someone asks what mission they play against an opponent's disposition, or how to set up a game in the current pack. grade-a-roster: Grade a Warhammer 40,000 army list with Praetorium, explain what it does well and lacks, compare it with winning tournament lists, and tune it with tested swaps. Use when someone asks how good their list is, what it is missing, how to improve it, or before handing over a list you built. import-a-list: Bring an army list from the official Warhammer 40,000 app, New Recruit, BattleBase or another builder into Praetorium, report what didn't match, and check, grade, save or export it. Use when someone pastes a list or exchange code, or asks to import, check or convert a list from another app. plan-a-matchup: Plan how a player's Warhammer 40,000 list takes on one opponent with Praetorium's simulator and mission data. Use when someone asks how to play their list against an army, which of their units handle the opponent's threats, or who should play the objectives. play-in-a-tournament: Take a signed-in player through a tournament, hidden-list game or group league: join, seal a list, find their table, start the battle and report the score. Use when someone asks what's due, wants to seal a list, or asks who they play next. review-a-battle: Summarise one of a signed-in player's Praetorium battles from its report, such as how the score built up, which stratagems were used and the turning points. Use when someone asks how a game went or wants a write-up of it. review-my-battles: Look back at a player's Praetorium battles and record, such as results against an army, win rates by detachment or mission pack, and leaderboard places. Use when someone asks how they've been doing, who they lose to, or to find a past game. set-up-a-battle: Start a Praetorium battle for a signed-in player and set the table in the order the game does, from opponent and armies to the first turn. Use when someone wants to start, create or set up a game to track. track-a-battle: Read a Praetorium battle and record what happens during play for a signed-in player, such as phases, command points, stratagems, scoring, casualties and undo. Use when someone asks about the score or state of their battle, or wants to record something that happened in it.

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": {
      "name": "<name>"
    },
    "name": "get_skill"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe skill to read.
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 / 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. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety needs no restating. The description adds real behavioral context: the payload is procedural guidance plus a tool ordering, and it should be consumed before acting. It does not say how large the guidance is or what happens if a skill is unavailable, which keeps it below 5.

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

Conciseness3/5

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

The purpose and workflow rule are front-loaded, which is good, but the bulk is a dense run-on catalogue of 13 skills crammed into one paragraph with no list formatting or line breaks. The content largely earns its place for routing, yet the presentation makes it harder to scan than it needs to be.

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 three-parameter routing tool with no output schema, the definition covers what it returns, when to call it, and how to choose each skill value, which is close to complete. It omits only minor operational detail such as the expected size or structure of the returned guidance.

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

Parameters4/5

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

Schema coverage is 100% and the enum is fully described in the schema, so the baseline is 3. The description earns above baseline by attaching a distinct scenario to each of the 13 enum values, giving meaning the schema's bare value list does not. The llm_model and conversation_id parameters are left entirely to the schema, which is acceptable but leaves a small gap.

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 opening sentence gives a specific verb and resource: it 'returns step-by-step guidance for a task, including the Warhammer 40,000 knowledge and tool order it needs.' That distinguishes it clearly from data-returning siblings like get_reference or get_my_roster, which fetch records rather than procedural guidance.

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 gives an explicit workflow rule ('Read the matching skill before starting the task') and then supplies per-value 'Use when...' routing criteria for all 13 skills, so an agent can pick the right enum value from a user request without guessing. This is about as explicit as when-to-use guidance gets.

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