Skip to main content
Glama

Edit quiz

edit_quiz
DestructiveIdempotent

Read the quiz first. You can reapply earlier content from this chat on any plan. Edit the quiz with one ordered batch of changes using stable slide IDs and the revision returned by read_quiz. An update merges specified fields, preserving other content. Arrays replace the whole named list. Example: {action:"update",slideId:"q1",question:"Why does water evaporate?"}. Set or clear the explanation with {action:"update",slideId:"q1",explanation:"..."}, null removes it. An add takes a complete Rondilo slide with a fresh id. Give the user the editorUrl to open the quiz. A shared quiz also returns a review link for the host.

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": {
      "quizId": "<quizId>",
      "baseRevision": "<baseRevision>",
      "operationId": "<operationId>",
      "changes": "<changes>"
    },
    "name": "edit_quiz"
  }
}

Input Schema

NameRequiredDescriptionDefault
quizIdYes
changesYes
libraryNoUse personal for My quizzes, or organization when the user asks for their organization library. Omitting the library selects personal.
operationIdYesGenerate one UUID per batch; reuse it exactly on a retry.
baseRevisionYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description discloses the merge semantics that matter most: updates preserve unspecified fields, arrays replace the whole named list, null clears the explanation. It also describes returns (editorUrl, review link for shared quizzes) even though there is no output schema, and ties retries to a stable operationId base revision.

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 precondition, then the batch model, then per-action rules and examples; almost every sentence carries information. The explanation-clearing rule is stated twice (prose plus example), a small redundancy in an otherwise tight definition.

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 destructive batch mutation with no output schema, the description covers prerequisites, merge vs. replace semantics, and return links. It does not say whether a batch is applied atomically when a later change fails, nor what a stale baseRevision produces, which an agent preparing a large batch would want to know.

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 only 40%, and the description compensates by explaining baseRevision's provenance (the revision from read_quiz) and the per-action meaning of slideId, afterSlideId, and slide contents. It gives concrete payload examples for update and explanation clearing. The library enum and operationId semantics are left to the schema, which already documents them.

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 states a specific verb and resource (edit the quiz) and adds scope: one ordered batch of changes keyed by stable slide IDs and a base revision. The sibling read_quiz is named as the required prerequisite, so an agent can separate reading from editing immediately.

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?

"Read the quiz first" establishes the prerequisite and the batch framing tells the agent to group changes instead of firing one-off edits. It also gives a post-edit action (hand the user the editorUrl). It does not name alternatives for single small edits or exclusions, so it stops short of full routing guidance.

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