Skip to main content
Glama

Attach picture or sound

attach_quiz_media
DestructiveIdempotent

Attach one picture or sound to an existing slide. First read the quiz to obtain the slide ID and revision. Use a file the person supplied or one made in this chat. Where available, pass the chat file. A client with the exact bytes can send base64 for a file up to 256 KiB; never transcribe or invent encoded file contents. For a picture found on the web, pass imageUrl: a direct https link to the image file itself (JPEG, PNG, WebP, GIF or AVIF), not to a page that shows it. Only use pictures the person may use. If a link is refused, try another direct image link. If you cannot supply the image or sound, tell the person to add it in the existing Rondilo editor. Local paths are not files. A shared quiz accepts one suggestion at a time. Give the host its review link and wait for approval before attaching another file.

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": {
      "operationId": "<operationId>",
      "quizId": "<quizId>",
      "slideId": "<slideId>",
      "baseRevision": "<baseRevision>",
      "kind": "<kind>"
    },
    "name": "attach_quiz_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
quizIdYes
libraryNoUse personal for My quizzes, or organization when the user asks for their organization library. Omitting the library selects personal.
slideIdYes
imageUrlNoA direct https link to a picture file. Pictures only.
bytesBase64No
operationIdYesOne UUID per attachment. Reuse for retries.
baseRevisionYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: a 256 KiB ceiling on base64, the revision requirement implying conflict handling, a prohibition on inventing encoded bytes, an accepted-format list for imageUrl, and the shared-quiz approval gate. The notable gap is that destructiveHint=true is never explained — nothing says whether attaching replaces existing media on the slide, which is the one behavior an agent most needs before calling.

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?

Purpose is front-loaded and most sentences carry distinct operational facts (size cap, format list, approval flow, editor fallback). It is on the long side and the fallback advice is spread across several sentences, but little is genuinely redundant.

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 an 8-parameter mutating tool with no output schema, the definition covers the full happy path, the alternative input channels, and the failure fallback, so an agent can act without guessing. It stops short of describing what the mutation does to pre-existing slide media, which is the remaining hole given destructiveHint=true.

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 38% schema coverage, the description compensates well: it explains imageUrl must be a direct https link to the file rather than a page showing it (with accepted formats), that bytesBase64 is for clients holding exact bytes and is capped at 256 KiB, and that baseRevision comes from a prior read. It leaves operationId (documented in schema) and library unaddressed, but the schema covers library adequately.

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?

"Attach one picture or sound to an existing slide" is a precise verb + resource + scope, and the singular "one" plus "existing slide" distinguishes it from the quiz-creation and editing siblings. An agent knows immediately this is a media-add operation on an already-created slide, not a quiz-level write.

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?

Explicit sequencing ("First read the quiz to obtain the slide ID and revision"), an explicit source preference (chat file first, then base64, then imageUrl), and explicit fallbacks when a link is refused or nothing can be supplied ("tell the person to add it in the existing Rondilo editor"). It also states the shared-quiz constraint: one suggestion at a time, hand over the review link and wait for approval.

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