Skip to main content
Glama

Save a quiz you wrote on Tjaz

save_quiz

Saves a multiple-choice quiz whose questions are already written, by the user or by you, on Tjaz, and gives back a link to play it alone, in a 3D game or together on a big screen, and to share it. Use this when the user has the questions, e.g. pasted them, or asks you to write them. Tjaz checks the quiz against its terms before saving it

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": {
      "title": "<title>",
      "language": "<language>",
      "questions": "<questions>"
    },
    "name": "save_quiz"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYesA short title, at most 8 words
publicNoWhether the user wants it on tjaz.com/quizzes, where anyone can find it. A quiz from a chat is saved for those who get its link only; the user can show it on tjaz.com/quizzes from its Share dialog on tjaz.com
playersNoWho will play the quiz. An age group: children (6–12), teens (13–17), adults (18–64), seniors (65+); or, for school, a level: grade0 is the first year of school at about 6 (kindergarten, Danish 0. klasse), grade1 to grade12 the school years after it (grade4 is US Grade 4, Danish 4. klasse, German 4. Klasse, UK Year 5; grade10–grade12 are the last three years of upper secondary school, e.g. Danish 1.g–3.g), then bachelor, master, phd, or nobel for experts. Leave it out when the user didn't say who will play: Tjaz then reads it from the description, as tjaz.com does
languageYesThe language of the quiz: the language's code as Tjaz has it, ISO 639-1, e.g. da, en, ar, uk, and nb for Norwegian
questionsYes

Output Schema

NameRequiredDescriptionDefault
quizNo
statusYes
messageNoWhy it was refused, or what to tell the user

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / quiz / properties / links / properties / team
      Added value: +{
      +  "description": "Plays it on a big screen as one team against cute, silly monsters, everyone answering on their phone or laptop: the more answer right, the better the team defends, and each monster becomes its friend. Good for a class or a group of children",
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / public / description
      Previous value: -"Also show it on tjaz.com/quizzes, where anyone can find it. Default false: only those who get the link can play it"New value: +"Whether the user wants it on tjaz.com/quizzes, where anyone can find it. A quiz from a chat is saved for those who get its link only; the user can show it on tjaz.com/quizzes from its Share dialog on tjaz.com"
  3. Changed1 schema field changed
    • changedOutput schema / properties / quiz / properties / links / properties / bigScreen / description
      Previous value: -"Plays it together on a big screen, everyone answering on their phone"New value: +"Plays it together on a big screen, everyone playing along on their phone or laptop"
  4. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write. The description adds genuine context beyond them: a terms check runs before saving, and a play/share link is returned. It does not disclose the non-idempotent risk (calling twice may create two quizzes) or what happens if the terms check fails.

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 action and the object, then the trigger condition, then a behavioral note. Mostly efficient, though the '3D game or big screen' promotional clause is expendable detail for an agent deciding whether to call it.

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?

With an output schema present, the description needn't explain return values, and annotations cover the safety profile, so what remains is purpose, trigger and validation behavior — all present. Only the idempotency/duplicate-save behavior and the make_quiz boundary are 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 description coverage is 80%, so the schema already carries title, language, players, public and question-level semantics in detail. The description adds no parameter guidance of its own and instead spends its words on purpose and output.

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 (saves a multiple-choice quiz with pre-written questions) and describes the result (a playable/shareable link). It distinguishes itself from make_quiz only obliquely, via 'questions are already written', and the later phrase 'or asks you to write them' blurs the boundary rather than sharpening it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

'Use this when the user has the questions, e.g. pasted them, or asks you to write them' gives one positive trigger, but no when-not and no explicit routing to siblings such as make_quiz or translate_quiz. The trigger may overlap with make_quiz, leaving the agent to infer the split.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources