RooQuiz

Update question

update_question

Destructive

Update a single question of an existing form, located by code. Changeable: name / description / explain / required / score / correctAnswer / aiMatch (FillBlank AI grading) / precision (DateField/TimeField picker precision) / min / max / unit / decimalPlaces (NumberField) / words (Rate scale labels) / choices (replaces ALL choices of a choice-based question). NOT changeable — delete_question then add_question instead: question type, Rate steps, DropDown multiple, Ordering shuffle. DateField / TimeField / Rate reject score / correctAnswer / aiMatch (configure date/time scoring in the web app). The scored_quiz and outcome_quiz scenes reject the top-level score / correctAnswer / aiMatch as well: pass choices carrying choices[i].score or choices[i].outcomes instead (TrueFalse outcome votes still need delete + recreate). Display blocks are edited here too, with their own keys: Statement takes content, Swiper takes items (replacing all slides), and both take name / description — every question key is rejected on them.

Input Schema

TableJSON Schema

Name	Required	Description
`max`	No	NumberField only: new maximum allowed value; pass null to remove the upper bound. Ignored for other question types.
`min`	No	NumberField only: new minimum allowed value; pass null to remove the lower bound. Ignored for other question types.
`code`	Yes	Question code (field.code), from the get_form / create_form return value
`name`	No	New question stem, optional
`unit`	No	NumberField only: new display unit suffix (e.g. "kg"); pass null or an empty string to clear. Ignored for other question types.
`items`	No	Swiper block only: replace ALL slides with this list (1-10). Slides get fresh ids, so any translated slide titles / notes for this block have to be rewritten afterwards.
`score`	No	Score for this question; 0 or omitted + no correctAnswer means not scored
`words`	No	Rate only: new scale labels shown under the rating control (up to 5); pass null or [] to remove the labels. Ignored for other question types.
`formId`	Yes	The form ID the question belongs to
`aiMatch`	No	FillBlank AI grading config (knowledge_quiz scene only). Pass an object to enable AI matching (requires the question to have correctAnswer + score > 0); pass null to turn it off and revert to exact-match grading. Omit to leave the existing grading mode untouched.
`choices`	No	Replace ALL choices of a choice-based question (SingleCheck / MultiCheck / DropDown / Ordering / Cascade; rejected for other types). To keep an existing choice's identity (so past answers still match it) pass its current code from get_form; entries without a code get a new auto-generated code. knowledge_quiz scene: if the existing correctAnswer references a code missing from the new choices, pass a new correctAnswer in the same call. scored_quiz scene: set choices[i].score to rebuild Option Scoring (required if the question currently has Option Scoring). outcome_quiz scene: every choice must carry an outcomes vote list (use [] for a neutral choice).
`content`	No	Statement block only: the new body text, which is the whole block. Same rich-text rules as description. It cannot be emptied — delete_question the block if you no longer want it. This field also accepts an inline image: put an <img src="..."> in it, where src is a direct image URL that renders in <img src> (a page URL that merely contains an image does not work). Use finalize_image_upload to host an image yourself, or a direct URL the user supplied. Never invent an image URL — omit the image instead of risking a broken one.
`explain`	No	New answer explanation (the question's "answer explanation" field, not the question note); pass an empty string to clear. Same rich-text rules as description.
`required`	No	Whether the question is required
`precision`	No	DateField / TimeField only: new picker precision. DateField accepts year \| month \| day \| hour \| minute \| second; TimeField accepts only minute \| second. Ignored for other question types.
`trueLabel`	No	TrueFalse only: new custom display text for the "true" option; pass an empty string to clear and fall back to the localized default. Ignored for other question types.
`falseLabel`	No	TrueFalse only: new custom display text for the "false" option; pass an empty string to clear and fall back to the localized default. Ignored for other question types.
`description`	No	New question note; pass an empty string to clear. This field also accepts an inline image: put an <img src="..."> in it, where src is a direct image URL that renders in <img src> (a page URL that merely contains an image does not work). Use finalize_image_upload to host an image yourself, or a direct URL the user supplied. Never invent an image URL — omit the image instead of risking a broken one.
`correctAnswer`	No	New correct answer; the shape follows the question type — see the anyOf branches. Choices are referenced by label or code (use the code when the same label repeats), and they must exist in the question's current choices, or in the `choices` replacement passed in this same call. NumberField answers must stay typeable within min / max and decimalPlaces. Rejected for DateField / TimeField / Rate, and in the scored_quiz / outcome_quiz scenes.
`decimalPlaces`	No	NumberField only: new number of decimal places allowed (0 = integers only); pass null to reset to the default 0. Ignored for other question types.

Output Schema

TableJSON Schema

Name	Required	Description
`code`	No	The question that was updated
`field`	No	The question after the merge
`formId`	No	The form that was edited
`changed`	No	Which question attributes this call changed

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 5, 2026

added

Input schema / properties / choices / items / properties / children / items / properties / children / items / properties / dimensionScores

Added value: +{
+  "additionalProperties": {
+    "maximum": 100,
+    "minimum": 0,
+    "type": "number"
+  },
+  "description": "scored_quiz scene only: the points this choice adds to each dimension when selected, as a map of dimension code → score, e.g. { \"dim_d\": 3, \"dim_i\": 1 }. Any choice carrying it switches the question to per-dimension scoring: for each dimension the question contributes the selected choices' scores for that dimension (a dimension not listed on the chosen choice counts 0), and a dimension without a formula automatically sums these contributions across questions. Codes must exist in report.dimensionAnalysis.dimensions — give dimensions[].code and reference them in the same create_form call. `score` remains the overall score fed to report.formula. Rejected in the knowledge_quiz / outcome_quiz scenes.",
+  "type": "object"
+}

addedInput schema / properties / choices / items / properties / children / items / properties / dimensionScores

Added value: +{
+  "additionalProperties": {
+    "maximum": 100,
+    "minimum": 0,
+    "type": "number"
+  },
+  "description": "scored_quiz scene only: the points this choice adds to each dimension when selected, as a map of dimension code → score, e.g. { \"dim_d\": 3, \"dim_i\": 1 }. Any choice carrying it switches the question to per-dimension scoring: for each dimension the question contributes the selected choices' scores for that dimension (a dimension not listed on the chosen choice counts 0), and a dimension without a formula automatically sums these contributions across questions. Codes must exist in report.dimensionAnalysis.dimensions — give dimensions[].code and reference them in the same create_form call. `score` remains the overall score fed to report.formula. Rejected in the knowledge_quiz / outcome_quiz scenes.",
+  "type": "object"
+}

addedInput schema / properties / choices / items / properties / dimensionScores

Added value: +{
+  "additionalProperties": {
+    "maximum": 100,
+    "minimum": 0,
+    "type": "number"
+  },
+  "description": "scored_quiz scene only: the points this choice adds to each dimension when selected, as a map of dimension code → score, e.g. { \"dim_d\": 3, \"dim_i\": 1 }. Any choice carrying it switches the question to per-dimension scoring: for each dimension the question contributes the selected choices' scores for that dimension (a dimension not listed on the chosen choice counts 0), and a dimension without a formula automatically sums these contributions across questions. Codes must exist in report.dimensionAnalysis.dimensions — give dimensions[].code and reference them in the same create_form call. `score` remains the overall score fed to report.formula. Rejected in the knowledge_quiz / outcome_quiz scenes.",
+  "type": "object"
+}

Changed2 schema fields changedAug 26, 2026

addedInput schema / properties / content

Added value: +{
+  "description": "Statement block only: the new body text, which is the whole block. Same rich-text rules as description. It cannot be emptied — delete_question the block if you no longer want it. This field also accepts an inline image: put an <img src=\"...\"> in it, where src is a direct image URL that renders in <img src> (a page URL that merely contains an image does not work). Use finalize_image_upload to host an image yourself, or a direct URL the user supplied. Never invent an image URL — omit the image instead of risking a broken one.",
+  "maxLength": 5000,
+  "type": "string"
+}

addedInput schema / properties / items

Added value: +{
+  "description": "Swiper block only: replace ALL slides with this list (1-10). Slides get fresh ids, so any translated slide titles / notes for this block have to be rewritten afterwards.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "description": {
+        "description": "Optional slide note. Web editor only, same as title.",
+        "maxLength": 1000,
+        "type": "string"
+      },
+      "image": {
+        "description": "The slide image: a media ID returned by finalize_image_upload, or the media URL of an image already in this team library. Required — the answer page renders the images and nothing else.",
+        "type": "string"
+      },
+      "title": {
+        "description": "Optional slide label. Shown in the web editor only (the answer page renders the image), and translatable per language.",
+        "maxLength": 200,
+        "type": "string"
+      }
+    },
+    "required": [
+      "image"
+    ],
+    "type": "object"
+  },
+  "maxItems": 10,
+  "minItems": 1,
+  "type": "array"
+}

First observedAug 24, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already mark this as a read/write destructive operation (readOnlyHint=false, destructiveHint=true), and the description adds substantial behavioral depth beyond that: choices replacement destroys existing identities unless codes are reused, Swiper slides get fresh IDs requiring translation rewrites, and scene-specific rejections are spelled out. This is exactly the kind of context annotations cannot carry.

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 prose is dense and long, but every sentence carries operational information — no filler or repetition of the title. It is front-loaded with the core purpose, then the changeable list, then restrictions, and then display-block specifics. A bulleted structure would improve scannability, but for the complexity covered the text is efficiently organized.

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 20-parameter mutation tool with scene-dependent behavior, display-block variants, and destructive replacement semantics, the description covers all the essential ground: what can change, what cannot, how to achieve the unchangeable, scene rejections, replacement side effects, and inline image handling. An output schema is present, so return values don't need to be described. Nothing an agent needs to invoke this 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 input schema already documents every parameter richly. The description still adds value by summarizing cross-cutting constraints (scene-level rejections of score/correctAnswer/aiMatch, display-block key separation, and the not-changeable list) that aren't obvious from any single parameter. It doesn't invent new per-parameter meaning, but it does orient the agent before it reads the schema.

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 opens with a specific verb and resource: 'Update a single question of an existing form, located by code.' It clearly enumerates changeable fields and explicitly contrasts with the delete_question + add_question workflow for unchangeable attributes, distinguishing this tool from its siblings add_question, delete_question, and insert_question.

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?

Provides explicit when-to-use and when-not-to-use guidance: it names the alternative workflow ('NOT changeable — delete_question then add_question instead'), spells out which scenes reject which fields, and states that choices 'replaces ALL choices' so the agent knows the destructive implication of passing that parameter. No relevant usage context is left to inference.

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?