Skip to main content
Glama

Search the Praetorium game reference

search_reference
Read-onlyIdempotent

Searches Praetorium’s missions, force dispositions, deployments, terrain, rules, detachments, and datasheets by name, number, keyword, and value, then datasheets and detachments whose abilities, stratagems or enhancements say the words searched for, such as objective control remains for an ability that keeps an objective. Returns bounded excerpts with canonical URLs, source revisions, and attribution; a match found by what an ability says names that ability and points at its section. Rules text is not included; records point to it upstream.

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": {
      "query": "<query>"
    },
    "name": "search_reference"
  }
}

Input Schema

NameRequiredDescriptionDefault
packNo
kindsNo
limitNo
queryYesA name, a printed rule number, an ability, a weapon, or a keyword.
cursorNo
factionNo
documentNo
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.

Output Schema

NameRequiredDescriptionDefault
queryYes
resultsYes
revisionsYes
nextCursorYes

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. Changed3 schema fields changed
    • changedInput schema / properties / kinds / items / enum
      Previous value: -[
      -  "datasheet",
      -  "deployment",
      -  "detachment",
      -  "mission",
      -  "rule",
      -  "terrain"
      -]New value: +[
      +  "datasheet",
      +  "deployment",
      +  "detachment",
      +  "disposition",
      +  "mission",
      +  "rule",
      +  "terrain"
      +]
    • changedInput schema / properties / kinds / maxItems
      Previous value: -6New value: +7
    • changedOutput schema / properties / results / items / properties / kind / enum
      Previous value: -[
      -  "datasheet",
      -  "deployment",
      -  "detachment",
      -  "mission",
      -  "rule",
      -  "terrain"
      -]New value: +[
      +  "datasheet",
      +  "deployment",
      +  "detachment",
      +  "disposition",
      +  "mission",
      +  "rule",
      +  "terrain"
      +]
  3. Changed4 schema fields changed
    • addedOutput schema / properties / results / items / properties / excerpt / maxLength
      Added value: +322
    • addedOutput schema / properties / results / items / properties / section / properties / textSources / description
      Added value: +"Where withheld rules text lives upstream: the pinned file, its source, and the id of the record holding it there when the file has one. Fetch it there if you need the wording."
    • addedOutput schema / properties / results / items / properties / section / properties / textSources / items / properties / url / format
      Added value: +"uri"
    • addedOutput schema / properties / results / maxItems
      Added value: +25
  4. Changed2 schema fields changed
    • changedInput schema / properties / query / description
      Previous value: -"Words, a printed rule number, an ability, a weapon, or a rules phrase."New value: +"A name, a printed rule number, an ability, a weapon, or a keyword."
    • addedOutput schema / properties / results / items / properties / section / properties / textSources
      Added value: +{
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "id": {
      +        "type": "string"
      +      },
      +      "source": {
      +        "enum": [
      +          "bsdata",
      +          "game-datacards"
      +        ],
      +        "type": "string"
      +      },
      +      "url": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "source",
      +      "url"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  5. First observed

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive, non-open-world behavior, so the bar is lower; the description still adds real value by disclosing the return shape (bounded excerpts with canonical URLs, source revisions, attribution) and the important limitation that rules text is not returned, only pointers upstream. It does not discuss result limits, pagination behavior, or how exhaustive matches are, which keeps it from a 5.

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 verb and scope, and nearly every clause adds information about search scope or return shape. There is mild redundancy — datasheets and detachments are enumerated twice across the two sentences, and the 'objective control remains' example is wordy — but no filler.

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

Completeness3/5

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

An output schema exists, so the prose recap of return values is optional rather than necessary. The gaps that matter are the undocumented filter/pagination parameters and the absence of guidance on how to proceed from an excerpt to the full record, which is the obvious next step after a search result.

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

Parameters2/5

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

Schema description coverage is only 33% across 9 parameters, so the description should compensate. It explains the query concept loosely (name, number, keyword, value) but says nothing about the filtering parameters (kinds, faction, document, pack), the limit ceiling, or the cursor mechanism — an agent has no textual guidance on how these narrow results or how to page.

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

Purpose4/5

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

States a specific verb and resource (search Praetorium's missions, dispositions, deployments, terrain, rules, detachments, datasheets) and spells out the match semantics: by name, number, keyword, and value, plus full-text matching of ability/stratagem/enhancement text. It implicitly separates itself from get_reference_record by noting it returns bounded excerpts that point upstream, but never names a sibling tool outright.

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

Usage Guidelines3/5

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

The description conveys when the tool applies (finding records by identifier or by what an ability says) and notes that rules text is not included, so records must be followed upstream. However, it never explicitly routes to get_reference_record or list_reference, nor states when a direct lookup should be preferred over a search, leaving that inference to the agent.

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