Praetorium

Read one Praetorium reference result

get_reference

Read-onlyIdempotent

Reads the complete bounded document returned by search_reference, with its revisions and attribution. A section that withholds rules text lists textSources: the pinned upstream file and record id to fetch if you need the wording.

Input Schema

Name	Required	Description	Default
`id`	Yes	A reference id such as datasheet:necrons:necron-warriors: a result id from search_reference, a mission pack id from list_reference, or a referenceId from list_units or simulate_combat. Names, URLs, and unit ids are not reference ids.

Output Schema

Name	Required	Description	Default
`id`	Yes
`url`	Yes
`kind`	Yes
`title`	Yes
`faction`	Yes
`sections`	Yes
`revisions`	Yes
`attribution`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 26, 2026

changedInput schema / properties / id / description

Previous value: -"The stable result id returned by search_reference."New value: +"A reference id such as datasheet:necrons:necron-warriors: a result id from search_reference, a mission pack id from list_reference, or a referenceId from list_units or simulate_combat. Names, URLs, and unit ids are not reference ids."

Changed2 schema fields changedOct 26, 2026

changedOutput schema / properties / sections / items / properties / textSources / description

Previous value: -"Where withheld rules text lives upstream; fetch it there if you need the wording."New 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 / sections / items / properties / textSources / items / properties / url / format
```
Added value: +"uri"
```

Changed1 schema field changedOct 17, 2026

addedOutput schema / properties / sections / items / properties / textSources

Added value: +{
+  "description": "Where withheld rules text lives upstream; fetch it there if you need the wording.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "source": {
+        "enum": [
+          "bsdata",
+          "game-datacards"
+        ],
+        "type": "string"
+      },
+      "url": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "source",
+      "url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

First observedSep 28, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavior beyond them: the document is bounded, includes revisions and attribution, and sections may withhold rules text while exposing textSources with a pinned upstream file and record id. That withholding behavior is the kind of thing an agent could not infer. It omits error behavior for ids that don't resolve.

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

Conciseness5/5

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

Two sentences, front-loaded with what is returned, followed by the one non-obvious edge case. Nothing is wasted and nothing important is buried.

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?

With an output schema present and annotations covering safety, the description correctly focuses on the withheld-text path rather than return shapes. The remaining gap is the lack of differentiation from get_reference_record, a sibling whose name strongly overlaps.

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

Parameters3/5

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

Schema coverage is 100%, so the 'id' parameter and its accepted sources are fully documented in the schema itself. The description adds no format or validation detail beyond that, so baseline 3 applies.

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 ('Reads the complete bounded document... with its revisions and attribution') and anchors it to the sibling that produces the id (search_reference). It does not differentiate itself from the sibling get_reference_record, which an agent must distinguish by name alone.

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?

Clear usage context: this is the fetch step that follows search_reference, and it names the fallback path (textSources) for withheld rules text. It stops short of stating when to use get_reference_record instead, so exclusions are missing.

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?