Skip to main content
Glama

Read unit options for a roster

get_unit_options
Read-onlyIdempotent

Lists what each named unit lets a roster pick set, with names first and the ids a pick takes beside them: its sizes, its toggles (key of the Warlord toggle: set toggles {key: 1} on exactly one CHARACTER), and every choice group (wargear, enhancement, detachment upgrade, unit composition) with its options' ids, points, how many the default loadout takes (taken), and per-option min and max. A choice whose set is choices takes {key: optionId}; omit an optional one to decline it. One whose set is spreads takes {key: {optionId: count}}, counts within each option's min and max, totalling no more than room and at least least; for 'every model one option' give the whole room to one option. A group whose key extends another's key and option id applies only while that option is taken. Enhancements and detachment upgrades appear only with a detachment, at their cost; a list takes each enhancement once, on a CHARACTER that is not an Epic Hero, and a unit holds at most one, counting the leaders and support units attached to it, which these options can't see; check_roster flags a second. roster gives the catalogueId, detachmentIds and dispositions a save_roster or check_roster roster takes. Leave out a choice to keep the default; check the finished list with check_roster.

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": {
      "faction": "<faction>",
      "units": "<units>"
    },
    "name": "get_unit_options"
  }
}

Input Schema

NameRequiredDescriptionDefault
unitsYesThe units to read options for, priced together as one list in this battle size and detachment.
factionYesFaction id, URL slug, or display name from list_reference or list_units.
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.
battleSizeNoThe roster limit in points.
detachmentNoDetachment id, slug, or name from list_units; enhancements and detachment upgrades are offered only under one.
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

A4.2/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds real context beyond that: the exact shape of returned choices ({key: optionId} vs {key: {optionId: count}}), counting constraints (within min/max, no more than room and at least least), enhancement restrictions (once per list, on a non-Epic-Hero CHARACTER, at most one per unit including unseen attached leaders), and the warning that check_roster flags a second.

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?

It is front-loaded with what gets returned, which is correct, and nearly every clause carries information. However, it is a single dense run-on paragraph with heavy parenthetical nesting and semicolon chains, making the encoding rules hard to parse on first read. The content earns its place; the packaging does not.

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 must carry the return shape, and it does so thoroughly: names and ids, sizes, toggles, choice groups with options, points, taken counts, and per-option min/max. It also explains the roster metadata block consumed by save_roster/check_roster, so nothing an agent needs to call and then use the result is missing.

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%, so the baseline is 3, but the description adds cross-field meaning: the units are 'priced together as one list in this battle size and detachment,' which explains how battleSize and detachment interact with the units array. It also clarifies that detachment must be supplied for enhancements to appear. It says nothing about llm_model or conversation_id, which are analytics-only and acceptable to skip.

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?

The description names a specific verb and resource: it 'lists what each named unit lets a roster pick,' covering sizes, toggles and choice groups with ids, points and min/max. It also distinguishes itself from check_roster (which flags conflicts) and save_roster (which consumes the returned roster), so an agent can place it in the workflow 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 Guidelines4/5

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

It gives concrete usage rules: omit a choice to keep the default, omit an optional choice to decline it, give the whole room to one option for 'every model one option,' and validate the finished list with check_roster. It also states that enhancements and detachment upgrades appear only when a detachment is supplied. What's missing is an explicit statement of when not to use it (e.g., for an existing saved roster, where get_my_roster applies).

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