Skip to main content
Glama

Create a quiz and invite friends

create_quiz
DestructiveIdempotent

Use for requests to make a quiz or game for friends, or to reuse an earlier quiz as a new game. Supply complete rounds, questions and answers. Creates a real editable lobby and returns host and invitation links. Free access and no contributions are defaults. Use paid single-edition access only with user authorization. Retry identical input with the same requestId, including after timeouts; never create a replacement quiz. Never starts gameplay. Summarize without revealing answers; follow-up edits target the returned runId.

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>",
      "requestId": "<requestId>",
      "blocks": "<blocks>"
    },
    "name": "create_quiz"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYes
accessNoFree access by default. Select an owned paid grant only with the user’s authorization; single-edition access is bound to the new game.
blocksYes
nicknameNoHost player name. Use Host when no name was supplied.Host
settingsNo
requestIdYesStable UUID for this intent. Reuse it with identical arguments after a lost response; use a new UUID for a different action.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=true, and the description meaningfully reinforces both: retry semantics with the same requestId ('never create a replacement quiz') explain the idempotency, and 'creates a real editable lobby' plus 'never starts gameplay' bound the side effects. It adds defaults (free access, no contributions) and an authorization gate for paid grants, which go beyond the structured fields. It also warns about not revealing answers when summarizing, a genuine behavioral constraint.

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 and dense with operational constraints; nearly every clause is actionable (defaults, authorization, retry, no gameplay). The clipped, imperative style is efficient but slightly staccato, and the trailing summarization instruction is somewhat tangential to invoking the tool.

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?

For a six-parameter, deeply nested, destructive create tool this covers the essentials: what is produced (lobby, host and invitation links), retry safety, access defaults, and what it does NOT do (start gameplay). Since an output schema exists, return-value detail is rightly omitted. Minor gaps remain around the settings object and nickname behavior, but nothing blocking.

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?

With only 50% schema description coverage, the description carries real weight: it clarifies that 'blocks' must contain complete rounds, questions and answers, explains the free-vs-paid access default, and explains how requestId should be reused. It says nothing about 'nickname' or the many 'settings' toggles, but the schema supplies defaults for those. Net effect is meaning added beyond the schema for the invocation-critical parameters.

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?

The description states a specific verb and resource ('make a quiz or game for friends'), plus the concrete effect ('Creates a real editable lobby and returns host and invitation links'), which tells an agent this is a create-and-publish operation rather than a read or edit. It also distinguishes follow-up work ('follow-up edits target the returned runId') from this call. One weak spot: 'reuse an earlier quiz as a new game' brushes against what a replay-style sibling might do, adding mild ambiguity.

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?

Clear conditions are given: use paid access only with user authorization, retry identical input with the same requestId rather than creating a replacement, and note that it never starts gameplay. That is strong when/when-not guidance. What is missing is explicit routing to named alternatives (e.g. update_quiz for edits, replay_game for reruns); the agent must infer which sibling handles post-creation editing from the runId hint.

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