Praetorium

List compact faction units for roster planning

list_units

Read-onlyIdempotent

Returns every pickable unit in one bounded response with unit-size costs, composition, attachment relationships, roster limits, roles, keywords, and links. Include a detachment, including one a chapter takes from its codex, to list only the units it allows and receive its rules, enhancements, upgrades, and stratagems by name, cost, and timing without opening every unit page. Their rules text is at each record’s textSources. A unit’s points is what its smallest size costs in this battle size and detachment, including any wargear or enhancement the detachment makes it take; costs is the Munitorum Field Manual table for every size. Legends and Crucible datasheets are left out unless nonMatchedPlay is true. A large faction such as a Space Marine chapter can exceed what an assistant reads at once, so pass query to list only the units whose name or keywords contain it.

Input Schema

Name	Required	Description
`query`	No	List only units whose name or keywords contain this text, such as Terminator or Character.
`faction`	Yes	Faction id, URL slug, or display name from list_reference.
`battleSize`	No	Battle size in points for size-dependent limits.
`detachment`	No	Detachment id, slug, or display name.
`nonMatchedPlay`	No	Also list Legends and Crucible datasheets, which matched play does not allow.

Output Schema

Name	Required	Description	Default
`query`	Yes
`units`	Yes
`faction`	Yes
`revisions`	Yes
`battleSize`	Yes
`detachment`	Yes
`nonMatchedPlay`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedOct 30, 2026

addedInput schema / properties / nonMatchedPlay

Added value: +{
+  "default": false,
+  "description": "Also list Legends and Crucible datasheets, which matched play does not allow.",
+  "type": "boolean"
+}

addedInput schema / properties / query

Added value: +{
+  "description": "List only units whose name or keywords contain this text, such as Terminator or Character.",
+  "maxLength": 160,
+  "minLength": 1,
+  "type": "string"
+}

addedOutput schema / properties / nonMatchedPlay
```
Added value: +{
+  "type": "boolean"
+}
```

addedOutput schema / properties / query

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / units / items / properties / costs / items / properties / copies
```
Added value: +{
+  "type": "string"
+}
```
changedOutput schema / properties / units / items / properties / costs / items / properties / detachment / type
```
Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
```
changedOutput schema / properties / units / items / properties / costs / items / properties / faction / type
```
Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
```
changedOutput schema / properties / units / items / properties / costs / items / properties / keyword / type
```
Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
```

changedOutput schema / properties / units / items / properties / costs / items / required

Previous value: -[
-  "models",
-  "cost",
-  "keyword",
-  "faction",
-  "detachment"
-]New value: +[
+  "models",
+  "cost"
+]

changedOutput schema / required

Previous value: -[
-  "faction",
-  "battleSize",
-  "detachment",
-  "units",
-  "revisions"
-]New value: +[
+  "faction",
+  "battleSize",
+  "nonMatchedPlay",
+  "query",
+  "detachment",
+  "units",
+  "revisions"
+]

Changed1 schema field changedOct 26, 2026

changedOutput schema / properties / units / items / properties / limit / anyOf

Previous value: -[
-  {
-    "maximum": 9007199254740991,
-    "minimum": -9007199254740991,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maximum": 9007199254740991,
+    "minimum": 0,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

First observedSep 28, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds substantial context: Legends and Crucible are excluded unless nonMatchedPlay, rules text lives at textSources, and points vs costs are defined precisely. These are behavioral facts not present in annotations.

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 return behavior and dense with useful detail, with little filler. The points/costs sentence is long and slightly convoluted, costing a bit of readability.

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 an output schema present, the description needn't explain return shape, and it still covers filtering, exclusions, detachment semantics, and size-dependent cost behavior. An agent has everything needed to call it correctly.

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 baseline is 3, but the description goes beyond the schema by clarifying that query matches name or keywords, that detachment scopes results to allowed units, and by distinguishing 'points' from 'costs'. This adds real meaning over the field descriptions.

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 first sentence states a specific verb and resource ('Returns every pickable unit') plus the exact fields returned and that the response is bounded. This is clearly distinguishable from reference-listing siblings like list_reference or list_factions.

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 conditions: include a detachment to list only its allowed units, and pass query for large factions that exceed a single read. It does not explicitly name sibling alternatives, but the internal query/no-query and detachment/no-detachment guidance is clear.

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

All Praetorium tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?