Skip to main content
Glama

RooQuiz

by com.rooquiz.payload
OverviewDiscussionsAdmin

Update form translation

update_form_translation
Destructive

Save translated copy for one language version of a form. Pass the translated title / description / fields / report / systemText / booking / feedback, mirroring the shape returned by get_form_translation; fields you omit keep their current value and partial translation is allowed. Translation fields[] must not introduce codes that do not exist on the source form. Pass isActive=false to pause just this language version, independently of the form's overall isActive.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleNoTranslated form title
fieldsNoTranslated questions mirroring the source structure: same codes, translated text. The current draft comes from get_form_translation (or the clone create_form_translation returns) — edit the text in place and send it back. Merging is by code, not position, so a partial list is fine and omitted questions stay untranslated.
formIdYesThe source form UUID
reportNoTranslated report display text, mirroring the stored report that get_form_translation returns — the nested overallAnalysis / dimensionAnalysis / outcomeAnalysis shape, NOT the flattened `report` input of create_form / update_form. Scores, formulas, thresholds and codes always come from the source; only the text keys below are applied.
bookingNoTranslated copy for the result-page booking block (the block that offers a call). Whether the block shows at all always comes from the source form — this only translates its wording. Omit a key or send it empty to keep falling back to the source text.
feedbackNoTranslated copy for the result-page feedback block. Whether it shows and its answer type always come from the source form — this only translates its wording. Replaced WHOLESALE on every save: pass every key you want translated; omitted or empty keys fall back to the source text. Read the source text and choice codes from feedbackSource in get_form_translation / create_form_translation.
isActiveNoEnable/pause this language version (independent of the form's overall isActive).
languageYesWhich language version to update
systemTextNoTranslated answer-page system copy, as an open key→text map (e.g. { "submitButton": "Absenden", "nextPage": "Weiter" }). Keys are the answer-page copy keys — read the ones already set from get_form_translation, and note that keys the answer page does not know are stored but never rendered. Every key is optional; an empty value falls back to the built-in text for this language.
descriptionNoTranslated form description

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
formIdNoThe source form
updatedNoWhich parts of the translation this call changed
languageNoLanguage that was saved

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / feedback
      Added value: +{
+  "additionalProperties": false,
+  "description": "Translated copy for the result-page feedback block. Whether it shows and its answer type always come from the source form — this only translates its wording. Replaced WHOLESALE on every save: pass every key you want translated; omitted or empty keys fall back to the source text. Read the source text and choice codes from feedbackSource in get_form_translation / create_form_translation.",
+  "properties": {
+    "buttonText": {
+      "description": "Translated submit button label.",
+      "maxLength": 30,
+      "type": "string"
+    },
+    "choices": {
+      "description": "Choice answer type only: translated option labels matched by the source choice code; a choice you leave out keeps the source label.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "code": {
+            "description": "Source choice code (from feedbackSource.choices)",
+            "type": "string"
+          },
+          "label": {
+            "description": "Translated label",
+            "maxLength": 100,
+            "type": "string"
+          }
+        },
+        "required": [
+          "code",
+          "label"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "description": {
+      "description": "Translated block description.",
+      "maxLength": 500,
+      "type": "string"
+    },
+    "question": {
+      "description": "Translated feedback question.",
+      "maxLength": 200,
+      "type": "string"
+    },
+    "title": {
+      "description": "Translated block heading.",
+      "maxLength": 100,
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  2. Changed3 schema fields changed
    • addedInput schema / properties / fields / items / properties / explain
      Added value: +{
+  "description": "Knowledge quiz: translated answer explanation shown in the answer review.",
+  "type": "string"
+}
    • addedInput schema / properties / report / properties / dimensionAnalysis / properties / dimensions / items / properties / levels / items / properties / cta
      Added value: +{
+  "additionalProperties": true,
+  "description": "Only the CTA button text is translatable; the link and its settings come from the source.",
+  "properties": {
+    "text": {
+      "description": "Translated CTA button text.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
    • addedInput schema / properties / report / properties / overallAnalysis / properties / levels / items / properties / cta
      Added value: +{
+  "additionalProperties": true,
+  "description": "Only the CTA button text is translatable; the link and its settings come from the source.",
+  "properties": {
+    "text": {
+      "description": "Translated CTA button text.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  3. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: fields merge by code while feedback is 'Replaced WHOLESALE on every save', unknown systemText keys are 'stored but never rendered', and isActive pauses only this language version independently of the form. This is precisely the mutation semantics an agent needs and that the destructiveHint alone could not convey.

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 core action, then the field list, merge rules, and constraint. Dense and slightly long, but nearly every clause carries distinct, load-bearing information, so little is wasted.

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?

Given an output schema exists, return values need not be described, and the description covers merge/replace semantics, key matching, and the isActive behavior. It omits any note on permissions/auth for this destructive write, which is the main remaining gap.

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 real meaning: the fields[] code constraint ('must not introduce codes that do not exist on the source form') and the merge-by-code vs wholesale-replace distinction. It stops short of resolving individual field formats, which the schema already handles.

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: 'Save translated copy for one language version of a form.' It clearly names the fields involved (title/description/fields/report/systemText/booking/feedback) and references get_form_translation as the shape source, distinguishing it from the read sibling. It does not explicitly contrast with create_form_translation or delete_form_translation, leaving the update-vs-create boundary to inference.

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?

Explains the workflow ('edit the text in place and send it back', draft comes from get_form_translation) and the merge behavior ('fields you omit keep their current value and partial translation is allowed'). It gives clear operating context but never explicitly names when to use this over create_form_translation or delete_form_translation for the same language version.

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

All RooQuiz toolsInspect
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