Skip to main content
Glama
Txpple

fvtt-mcp-molten5e

by Txpple
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

update-rolltable

Update a roll table's fields and results. Patch one entry's text, linked item, weight, or roll range in place, or replace all results at once.

Instructions

Update a RollTable's fields (name, description, formula, replacement, displayRoll) and/or its entries, two ways: editResults = TARGETED per-entry edits — name an entry by its roll face (e.g. 7 on a d12) or resultId (from get-rolltable) and patch just its text, linked uuid, weight, and/or range; every OTHER entry (ranges, weights, @UUID item links) stays byte-identical — the right way to fix a typo on one entry of a tuned table. text/uuid REPLACE that entry's content (copy the raw text from get-rolltable and change only what you need). results = DESTRUCTIVE whole-set replace (all entries deleted and recreated with auto-assigned ranges). Bad edits are isolated + reported; an introduced range overlap/gap is warned. GM-only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoNew table name.
formulaNoNew roll formula.
resultsNoDESTRUCTIVE: replaces ALL existing results (deleted + recreated with auto-assigned ranges). To change one entry, use editResults instead.
identifierYesTable id or exact name.
descriptionNoNew description.
displayRollNoShow the roll when drawing.
editResultsNoTARGETED per-entry edits — fix one entry's text/link/weight/range in place; every other entry (ranges, weights, @UUID item links) is left byte-identical. Mutually exclusive with `results`.
replacementNoDraw with replacement.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv2.1.3
    • addedInput schema / properties / editResults / items / properties / range / items
      Added value: +false
    • addedInput schema / properties / editResults / items / properties / range / maxItems
      Added value: +2
    • addedInput schema / properties / editResults / items / properties / range / minItems
      Added value: +2
    • addedInput schema / properties / results / items / properties / range / items
      Added value: +false
    • addedInput schema / properties / results / items / properties / range / maxItems
      Added value: +2
    • addedInput schema / properties / results / items / properties / range / minItems
      Added value: +2
  2. Changed2 schema fields changedv1.3.0
    • addedInput schema / properties / editResults
      Added value: +{
+  "description": "TARGETED per-entry edits — fix one entry's text/link/weight/range in place; every other entry (ranges, weights, @UUID item links) is left byte-identical. Mutually exclusive with `results`.",
+  "items": {
+    "properties": {
+      "name": {
+        "description": "Display label for the `uuid` link (default: the resolved document name).",
+        "minLength": 1,
+        "type": "string"
+      },
+      "range": {
+        "description": "New explicit [low, high] roll range for THIS entry only — other entries are untouched (an introduced overlap/gap is warned, not blocked).",
+        "prefixItems": [
+          {
+            "type": "integer"
+          },
+          {
+            "type": "integer"
+          }
+        ],
+        "type": "array"
+      },
+      "resultId": {
+        "description": "Target the entry by TableResult id (from get-rolltable) — always unambiguous.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "roll": {
+        "description": "Target the entry whose roll range covers this die face (e.g. 7 = \"entry 07\" on a d12). Errors if no entry — or more than one — covers it. Provide roll OR resultId.",
+        "type": "integer"
+      },
+      "text": {
+        "description": "REPLACE this entry's text (HTML / @UUID enrichers allowed — the raw current text is in get-rolltable; copy it and change only what you need). Combine with `uuid` via {{link}}.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "uuid": {
+        "description": "Re-link the entry to a REAL item by compendium/world UUID (premium-book only, SRD refused) — rendered as a clickable @UUID link, alone or into a {{link}} placeholder in `text`.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "weight": {
+        "description": "New relative weight for this entry.",
+        "exclusiveMinimum": 0,
+        "type": "integer"
+      }
+    },
+    "type": "object"
+  },
+  "minItems": 1,
+  "type": "array"
+}
    • changedInput schema / properties / results / description
      Previous value: -"If provided, replaces ALL existing results."New value: +"DESTRUCTIVE: replaces ALL existing results (deleted + recreated with auto-assigned ranges). To change one entry, use editResults instead."
  3. First observedv1.2.2

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and delivers: `results` deletes and recreates all entries, `editResults` leaves every other entry 'byte-identical', bad edits are 'isolated + reported', and range overlap/gap is 'warned, not blocked'. It also discloses the GM-only permission gate. This is rich, honest disclosure of side effects and failure behavior beyond anything the schema states.

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 long (~140 words across three sentences) but every clause earns its place; the tool genuinely has two complex modes that need explanation. It front-loads the core purpose and the editResults/results distinction before diving into details, and uses formatting cues to keep the structure scannable.

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?

For a complex 8-parameter mutation tool with no annotations and no output schema, the description plus rich schema covers purpose, both modes, destruction semantics, error reporting, permission requirements, and how to obtain identifiers. The only gap is the success return value/confirmation shape, which is minor given no output schema exists.

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% with already-detailed parameter descriptions, so the baseline is 3. The description adds meaningful semantics on top: it explains the targeting mechanism (roll face vs resultId), the byte-identical guarantee of editResults, and the destructive auto-assign behavior of results — semantics the schema alone does not synthesize.

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 description states a specific verb + resource ('Update a RollTable's fields ... and/or its entries') and goes further by distinguishing the two update modes (`editResults` targeted vs `results` destructive). It names `get-rolltable` as a companion for sourcing resultIds and raw text, differentiating itself from the read/lookup sibling without needing 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?

The description gives explicit in-tool usage guidance: `editResults` is 'the right way to fix a typo on one entry of a tuned table,' while `results` is flagged as a destructive whole-set replace. It also states the GM-only prerequisite and points to `get-rolltable` for the ids/text needed. It does not explicitly contrast with create/import/delete-rolltable siblings, but the mode-level guidance is clear and actionable.

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

Deploy Server

Other Tools