Skip to main content
Glama

RooQuiz

by com.rooquiz.payload
OverviewDiscussionsAdmin

Update form settings

update_form_settings
Destructive

Change how a form of the current team is delivered, as opposed to what it says (use update_form for title / questions / report / theme). Editable: submissionAccess (who may answer and whether seeing the report needs a login — this is the lead-capture gate), reportGateRequireCode (whether that login gate collects an emailed verification code, trading completion rate against lead quality), timeLimit, sharing (the result-page share button and personalised share card, which is what drives organic spread), answerSheet, booking (the result-page booking block that feeds the 1:1 call queue), gaTrackingId, sharedWithAll (whether every team member can see this form), and slug (the custom path that gives the public link a memorable, SEO-friendly address). Only the keys you pass are changed. Read the current values with get_form_share_info.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slugNoCustom path of the public answer link — the SEO-friendly address (e.g. quizster.app/<team>/burnout-test on the platform domain, or <custom-domain>/burnout-test when the team's custom domain is serving). Lowercase letters, digits and hyphens, 2-64 chars, must start and end with a letter or digit, unique within the team. Pass an empty string to clear back to the random address. Changing it breaks the previous custom path right away, but the token address (/a/<publicToken>) always keeps working and the page's canonical URL follows the custom path.
formIdYesThe form UUID
bookingNoThe result-page booking block. The bookable hours live in the team's booking settings, not here — this is only the switch and the copy. Bookings that come in are handled with list_bookings / review_booking.
sharingNoResult-page sharing: the share button, the personalised share card and the public summary. Turning this off stops respondents spreading their results.
timeLimitNoAnswer-time countdown. Only knowledge quizzes (knowledge_quiz / random_knowledge_quiz) can turn this on — a countdown makes sense when unanswered means wrong, but rushing a scorecard or a personality quiz just produces careless answers.
answerSheetNoThe answer-sheet sidebar on the answering page
crowdCompareNoShow respondents what share of people picked the same option ("62% of people chose the same as you"). Off by default: it publishes this quiz's answer distribution to whoever answers it, and seeing the majority choice nudges later respondents toward it — leave it off for quizzes used to match courses or place learners. Percentages only, never individual answers, and nothing shows until the quiz has 10+ submissions. Not available for knowledge quizzes at all: the distribution is effectively a crowdsourced answer key.
gaTrackingIdNoGoogle Analytics measurement id (G-XXXXXX) or Universal Analytics id (UA-XXXX-Y). Pass an empty string to clear.
sharedWithAllNoWhether every member of the team can see and open this form
submissionAccessNopublic = anyone answers and sees the report; login_to_view_report = anyone answers but must sign in to see the report (the default, this is how leads get captured); examinee_only = a login is required before answering at all
reportGateRequireCodeNoOnly applies when submissionAccess is login_to_view_report. false (the default for newly created quizzes) = the respondent only types an email and a name to see this one result — far more people finish, but the address is unverified and they get no account, and since result links do get forwarded, the report is effectively as reachable as public for whoever opens the link first. true = the respondent must confirm an emailed 6-digit code, so every captured lead has a verified address and the respondent gets an account they can return to. Quizzes created before this setting existed read as true.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
slugNoCustom path after this change; null when cleared (back to the random address)
formIdNoThe form that was changed
changedNoWhich settings this call changed
deliveryNoDelivery state: { isActive, submissionAccess, reportGateRequireCode, timeLimit, sharing, answerSheet, booking, gaTrackingId, sharedWithAll }; get_form_share_info adds the team-level examineeSignupDisabled (respondent self-signup off = a login-gated quiz turns away anyone not on the roster)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / crowdCompare / description
      Previous value: -"Show respondents what share of people picked the same option (\"62% of people chose the same as you\"). Off by default: it publishes this quiz's answer distribution to whoever answers it, and seeing the majority choice nudges later respondents toward it — leave it off for quizzes used to match courses or place learners. Percentages only, never individual answers, and nothing shows until the quiz has 20+ submissions. Knowledge quizzes show it only in the answer review after submitting, since mid-quiz it would give the answer away."New value: +"Show respondents what share of people picked the same option (\"62% of people chose the same as you\"). Off by default: it publishes this quiz's answer distribution to whoever answers it, and seeing the majority choice nudges later respondents toward it — leave it off for quizzes used to match courses or place learners. Percentages only, never individual answers, and nothing shows until the quiz has 10+ submissions. Not available for knowledge quizzes at all: the distribution is effectively a crowdsourced answer key."
  2. Changed1 schema field changed
    • addedInput schema / properties / crowdCompare
      Added value: +{
+  "additionalProperties": false,
+  "description": "Show respondents what share of people picked the same option (\"62% of people chose the same as you\"). Off by default: it publishes this quiz's answer distribution to whoever answers it, and seeing the majority choice nudges later respondents toward it — leave it off for quizzes used to match courses or place learners. Percentages only, never individual answers, and nothing shows until the quiz has 20+ submissions. Knowledge quizzes show it only in the answer review after submitting, since mid-quiz it would give the answer away.",
+  "properties": {
+    "enabled": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "enabled"
+  ],
+  "type": "object"
+}
  3. Changed2 schema fields changed
    • changedInput schema / properties / timeLimit / properties / minutes / description
      Previous value: -"Minutes allowed; required (>= 1) when enabling"New value: +"Minutes allowed; required when enabling, between 1 and 600"
    • addedInput schema / properties / timeLimit / properties / minutes / maximum
      Added value: +600
  4. Changed1 schema field changed
    • changedInput schema / properties / timeLimit / description
      Previous value: -"Answer-time countdown"New value: +"Answer-time countdown. Only knowledge quizzes (knowledge_quiz / random_knowledge_quiz) can turn this on — a countdown makes sense when unanswered means wrong, but rushing a scorecard or a personality quiz just produces careless answers."
  5. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag this as destructive and non-read-only; the description adds the partial-update behavior and gives context on downstream effects (lead capture, organic spread, booking queue). It does not enumerate consequences of every mutation, but the parameter schema covers those details.

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 front-loaded with purpose and alternative, followed by a compact but dense list of editable settings. It is long, yet there is little filler; however the 'Editable:' list is presented as exhaustive even though it omits crowdCompare.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The overall tool definition is rich (full schema, output schema, annotations), and the description supplies workflow guidance. But the natural-language 'Editable:' list omits crowdCompare, an updateable setting in the schema, which could mislead an agent into thinking it is not supported by this tool.

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 schema carries the parameter burden. The description still adds decision-relevant framing: submissionAccess is 'the lead-capture gate', reportGateRequireCode 'trading completion rate against lead quality', and sharing 'drives organic spread'.

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?

It opens with a specific verb and resource ('Change how a form ... is delivered') and immediately contrasts itself with update_form, which handles title/questions/report/theme. The listed editable fields make the tool's scope unmistakable.

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?

It explicitly names the sibling for content changes ('use update_form for title / questions / report / theme') and states the partial-update rule ('Only the keys you pass are changed'). It also points to get_form_share_info for reading current values, giving the agent a clear workflow.

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