Embers: Tabletop RPG Toolkit

Record a class-less character's existing classes

vault_record_pc_classes

The class-less on-ramp to the level-up flow. A hand-made character with no Class entries on its sheet can't level up (vault rejects the plan and the apply) — this tool records the class(es) and level(s) the character is ALREADY playing so the wizard can take over at the next level. It stamps identity snapshots ONLY: no features, proficiencies, HP, or trackables are granted — the sheet is trusted to already carry everything. Call vault_get_levelup_options first: RECORD mode (needsClassRecord: true) ships recordOptions[] (base classes with subclasses[] and subclassLevel) and totalLevel, the character's XP-derived level. The recorded levels must sum to EXACTLY that totalLevel (XP is the authority; vault never rewrites it) and a row may carry a subclass only at/above the option's subclassLevel. Rejected once any class entry exists. On success vault sets each class snapshot's stored level, attaches subclasses, updates core.class, appends a note, and returns { character, summary } — then call vault_get_levelup_options again for the normal chooser.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`classes`	Yes	One row per class the character already has, distinct classes only. The levels MUST sum to exactly the RECORD-mode chooser's `totalLevel` (the character's XP-derived level) — vault rejects any other split and never rewrites XP.
`characterId`	Yes	`_id` of the class-less character (must belong to the calling user).

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 25, 2026

addedInput schema / $schema

Added value: +"http://json-schema.org/draft-07/schema#"

addedInput schema / additionalProperties
```
Added value: +{}
```

addedInput schema / properties / characterId

Added value: +{
+  "description": "`_id` of the class-less character (must belong to the calling user).",
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / classes

Added value: +{
+  "description": "One row per class the character already has, distinct classes only. The levels MUST sum to exactly the RECORD-mode chooser's `totalLevel` (the character's XP-derived level) — vault rejects any other split and never rewrites XP.",
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "classRuleId": {
+        "description": "A base Class rule `_id` from the RECORD-mode chooser's `recordOptions[]._id`.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "level": {
+        "description": "The level the character already has in this class.",
+        "maximum": 20,
+        "minimum": 1,
+        "type": "integer"
+      },
+      "subclassRuleId": {
+        "description": "Optional: the subclass already picked, from the option's `subclasses[]._id`. Valid only when this row's level has reached the option's `subclassLevel` (a class picks its subclass at that level; null = no gate).",
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "classRuleId",
+      "level"
+    ],
+    "type": "object"
+  },
+  "minItems": 1,
+  "type": "array"
+}

addedInput schema / required

Added value: +[
+  "characterId",
+  "classes"
+]

First observedSep 21, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations declare this is a write operation that is not idempotent and not destructive; the description goes well beyond that, disclosing that only identity snapshots are stamped (no features, proficiencies, HP, or trackables), that levels must sum exactly to totalLevel, and that the tool sets stored levels, attaches subclasses, updates core.class, and appends a note. Destructive semantics could be slightly clearer given destructiveHint=false while the write mutates the sheet, but overall the disclosure is strong.

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?

The description is dense and front-loaded, leading with the reason the tool exists before the mechanics. It is on the long side and repeats some schema constraints verbatim, but nearly every sentence carries workflow or validation information an agent needs.

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?

For a constrained write tool with a rich input schema, an output schema, and full annotations, the description supplies the full workflow, validation rules, and side effects. Nothing an agent needs to invoke it correctly 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 the cross-row constraint that levels must sum to exactly totalLevel and that a subclass is valid only at/above the option's subclassLevel. That relational meaning is genuinely beyond the per-field schema text, though much of it is echoed rather than new.

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?

States a specific verb and resource (records the class(es) and level(s) a character is already playing) and explicitly frames it as the 'class-less on-ramp to the level-up flow', which cleanly separates it from siblings like vault_level_up_pc and vault_get_levelup_options. The agent can tell exactly what the tool does and when it is the wrong tool.

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?

Gives explicit prerequisites and sequencing: call vault_get_levelup_options first, work from RECORD mode (needsClassRecord: true), then call it again for the normal chooser. It also states the exclusion condition (rejected once any class entry exists), so both when-to-use and when-not-to-use are covered.

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

All Embers: Tabletop RPG Toolkit 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?