RooQuiz

Set dimension analysis

set_dimension_analysis

Destructive

Set the multi-dimension analysis (form.report.dimensionAnalysis) of a form, replacing the dimension list without touching overallAnalysis (title / radar settings you omit are kept). Dimension codes are stable: pass dimensions[].code to keep or set one, or omit it and a dimension with the same name keeps its existing code. Only scored_quiz forms have dimensions; every dimension needs a formula over question codes (e.g. {{q1}} + {{q2}}), where a question's choices[i].dimensionScores override its plain choice score for that dimension. A dimension still referenced by a question's dimensionScores or by report.formula (the overall formula) cannot be removed. Pass an empty dimensions array to clear the multi-dimension analysis. Call get_form first to read the question and dimension codes. Not supported for knowledge_quiz / outcome_quiz / ai_quiz forms.

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": {
      "formId": "<formId>"
    },
    "name": "set_dimension_analysis"
  }
}

Input Schema

Name	Required	Description
`title`	No	Multi-dimension analysis title
`formId`	Yes	The form ID to configure
`dimensions`	No	The dimension list (at most 50). Pass an empty array to clear the multi-dimension analysis.
`showRadarChart`	No	Whether to show the radar chart, default true
`showStandardLine`	No	Whether to show the standard-score line on the radar chart

Output Schema

Name	Required	Description
`formId`	No	The form that was edited
`dimensions`	No	The dimensions after the replace
`dimensionCount`	No	How many dimensions are configured now (0 = cleared)

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 31, 2026

removedInput schema / properties / dimensions / items / properties / fieldCodes

Removed value: -{
-  "description": "Required in the knowledge_quiz scene: the question codes this dimension covers (dimension score = sum of these field scores). Each code must exist in the form. Ignored in the scored_quiz scene, where the formula decides which questions count.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

changedInput schema / properties / dimensions / items / properties / formula / description

Previous value: -"Required in the scored_quiz scene: the dimension score formula, usually the sum of the questions in this dimension. Question codes must be wrapped in `{{code}}` (e.g. `{{q1}} + {{q2}}` when you set custom question codes, or `{{__field_abc}} + {{__field_def}}` for auto-generated ones); bare codes are rejected. Inside a dimension formula `{{q}}` is the question's score for THIS dimension: its choices[i].dimensionScores override when set, otherwise the plain choice score. A dimension formula cannot reference other dimensions (only report.formula can). Supported operators: + - * / ( ). Ignored in the knowledge_quiz scene."New value: +"Required: the dimension score formula, usually the sum of the questions in this dimension. Question codes must be wrapped in `{{code}}` (e.g. `{{q1}} + {{q2}}` when you set custom question codes, or `{{__field_abc}} + {{__field_def}}` for auto-generated ones); bare codes are rejected. Inside a dimension formula `{{q}}` is the question's score for THIS dimension: its choices[i].dimensionScores override when set, otherwise the plain choice score. A dimension formula cannot reference other dimensions (only report.formula can). Supported operators: + - * / ( )."

changedInput schema / properties / dimensions / items / properties / standardScore / description

Previous value: -"Standard score (the radar-chart standard line; in the scored_quiz scene it also acts as the dimension full mark). When omitted in the scored_quiz scene it defaults to the attainable maximum: the formula evaluated with every referenced question at its highest score for this dimension (choices[i].dimensionScores override, else the choice score); 0 when that cannot be estimated, e.g. the formula uses NumberField / date questions. knowledge_quiz defaults to 0."New value: +"Standard score: the radar-chart standard line and the dimension full mark. When omitted it defaults to the attainable maximum: the formula evaluated with every referenced question at its highest score for this dimension (choices[i].dimensionScores override, else the choice score); 0 when that cannot be estimated, e.g. the formula uses NumberField / date questions."

Changed4 schema fields changedSep 5, 2026

addedInput schema / properties / dimensions / items / properties / code

Added value: +{
+  "description": "Optional stable identifier for the dimension (same rules as question codes: starts with a letter or underscore, letters/digits/underscores only). Set it when questions reference the dimension via choices[i].dimensionScores in the same create_form call. When updating, pass the existing code to keep it; if omitted, a dimension with the same name keeps its current code, otherwise one is generated.",
+  "maxLength": 64,
+  "type": "string"
+}

changedInput schema / properties / dimensions / items / properties / fieldCodes / description

Previous value: -"Required in the knowledge_quiz scene: the question codes this dimension covers (dimension score = sum of these field scores). Each code must exist in the form. Ignored in the scored_quiz scene."New value: +"Required in the knowledge_quiz scene: the question codes this dimension covers (dimension score = sum of these field scores). Each code must exist in the form. Ignored in the scored_quiz scene, where the formula decides which questions count."

changedInput schema / properties / dimensions / items / properties / formula / description

Previous value: -"Required in the scored_quiz scene: the dimension score formula. Question codes must be wrapped in `{{code}}` (e.g. `{{q1}} + {{q2}}` when you set custom question codes, or `{{__field_abc}} + {{__field_def}}` for auto-generated ones); bare codes are rejected. Supported operators: + - * / ( ). Ignored in the knowledge_quiz scene."New value: +"Required in the scored_quiz scene: the dimension score formula, usually the sum of the questions in this dimension. Question codes must be wrapped in `{{code}}` (e.g. `{{q1}} + {{q2}}` when you set custom question codes, or `{{__field_abc}} + {{__field_def}}` for auto-generated ones); bare codes are rejected. Inside a dimension formula `{{q}}` is the question's score for THIS dimension: its choices[i].dimensionScores override when set, otherwise the plain choice score. A dimension formula cannot reference other dimensions (only report.formula can). Supported operators: + - * / ( ). Ignored in the knowledge_quiz scene."

changedInput schema / properties / dimensions / items / properties / standardScore / description

Previous value: -"Standard score (the radar-chart standard line; in the scored_quiz scene it also acts as the dimension full mark). Default 0."New value: +"Standard score (the radar-chart standard line; in the scored_quiz scene it also acts as the dimension full mark). When omitted in the scored_quiz scene it defaults to the attainable maximum: the formula evaluated with every referenced question at its highest score for this dimension (choices[i].dimensionScores override, else the choice score); 0 when that cannot be estimated, e.g. the formula uses NumberField / date questions. knowledge_quiz defaults to 0."

First observedAug 24, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, so the description's job is to say what is lost; it does — omitted title/radar settings are kept, dimensions still referenced by dimensionScores or report.formula cannot be removed, and an empty array wipes the analysis. It stops short of noting reversibility or anything about the response, so it is strong rather than complete.

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 operation and its non-destructive scope before the rules, and each sentence carries a distinct constraint (codes, formulas, removal restriction, clearing, inapplicable form types). It is dense and long, but the density is mostly justified by the domain.

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 destructive, nested-configuration mutation the description covers eligibility, prerequisite reads, code stability, removal guards and the clear-all case; with an output schema present it needn't describe return values. Nothing an agent needs before calling is missing.

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% and the schema already documents code stability, weight, levels, formula syntax and standardScore defaults in depth. The description reinforces the formula and code-keeping rules but adds little that isn't already spelled out in the schema text, so baseline 3 applies.

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?

Names a specific verb and resource ("Set the multi-dimension analysis (form.report.dimensionAnalysis) of a form") and states scope: the dimension list is replaced while overallAnalysis is preserved. An agent can tell this apart from question-level or overall-formula siblings 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 Guidelines5/5

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

Explicit prerequisites and exclusions: "Call get_form first to read the question and dimension codes" and "Not supported for knowledge_quiz / outcome_quiz / ai_quiz forms." It also gives the clearing condition (empty dimensions array), covering both when to use and when the tool is inapplicable.

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

All RooQuiz 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?