Skip to main content
Glama

Generate Carousel

carousels_board_generate
DestructiveIdempotent

Write and design a full carousel from a prompt into the project board: hook, body slides, ending call to action and a post caption, styled with the brand kit or a preset style, with optional AI photos (photos finish in the background; pendingAssetIds lists them). Replaces the current board and renames the project. Uses AI and image credits; a retry with the same idempotency key and input replays the first result without generating or charging again.

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": {
      "projectId": "<projectId>",
      "expectedRevision": "<expectedRevision>",
      "prompt": "<prompt>",
      "goal": "<goal>",
      "slideCount": "<slideCount>",
      "style": "<style>",
      "withImages": "<withImages>",
      "imageModelId": "<imageModelId>",
      "characterIds": "<characterIds>",
      "places": "<places>",
      "sourceUrl": "<sourceUrl>",
      "idempotencyKey": "<idempotencyKey>"
    },
    "name": "carousels_board_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYes
styleYesReady-made look; null keeps the carousel's current look.
placesYesSaved places to set the photos in (a Story Kit location); their reference photo keeps the same room. Empty lets the prompt decide.
promptYes
projectIdYesUUID string.
sourceUrlYesA public web page the carousel is about (full URL or domain); its text grounds the slides. Null reads a web address written in the prompt, if any.
slideCountYesTotal slides including cover and call to action; null lets the prompt decide.
withImagesYes
workspaceIdNo
characterIdsYesSaved AI characters to cast in the photos, by id; their saved references keep their faces. Empty lets the prompt decide.
imageModelIdYesImage model for the generated photos; null uses Nano Banana 2. Ignored when withImages is false.
idempotencyKeyYes
expectedRevisionYesReplace the board only at this revision; null replaces the latest board.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / imageModelId / anyOf
      Previous value: -[
      -  {
      -    "enum": [
      -      "fal-ai/nano-banana-2",
      -      "fal-ai/nano-banana-pro",
      -      "fal-ai/bytedance/seedream/v5/lite/text-to-image",
      -      "bytedance/seedream/v5/pro/text-to-image"
      -    ],
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "fal-ai/nano-banana-2",
      +      "fal-ai/nano-banana-pro",
      +      "bytedance/seedream/v5/pro/text-to-image",
      +      "bytedance/seedream/v5.5/text-to-image"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. Changed4 schema fields changed
    • addedInput schema / properties / characterIds
      Added value: +{
      +  "default": [],
      +  "description": "Saved AI characters to cast in the photos, by id; their saved references keep their faces. Empty lets the prompt decide.",
      +  "items": {
      +    "format": "uuid",
      +    "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      +    "type": "string"
      +  },
      +  "maxItems": 3,
      +  "type": "array"
      +}
    • addedInput schema / properties / imageModelId
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "fal-ai/nano-banana-2",
      +        "fal-ai/nano-banana-pro",
      +        "fal-ai/bytedance/seedream/v5/lite/text-to-image",
      +        "bytedance/seedream/v5/pro/text-to-image"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Image model for the generated photos; null uses Nano Banana 2. Ignored when withImages is false."
      +}
    • addedInput schema / properties / places
      Added value: +{
      +  "default": [],
      +  "description": "Saved places to set the photos in (a Story Kit location); their reference photo keeps the same room. Empty lets the prompt decide.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "locationId": {
      +        "maxLength": 120,
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "storyKitId": {
      +        "format": "uuid",
      +        "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "storyKitId",
      +      "locationId"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 3,
      +  "type": "array"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "projectId",
      -  "expectedRevision",
      -  "prompt",
      -  "goal",
      -  "slideCount",
      -  "style",
      -  "withImages",
      -  "sourceUrl",
      -  "idempotencyKey"
      -]New value: +[
      +  "projectId",
      +  "expectedRevision",
      +  "prompt",
      +  "goal",
      +  "slideCount",
      +  "style",
      +  "withImages",
      +  "imageModelId",
      +  "characterIds",
      +  "places",
      +  "sourceUrl",
      +  "idempotencyKey"
      +]
  3. Added

TDQS

A3.9/5.0
Behavior5/5

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

Annotations already flag destructive=true and idempotent=true, and the description adds substantive context on top: it spells out what is destroyed (the current board) and the side effect of renaming the project, that photos complete asynchronously with pendingAssetIds tracking them, that AI and image credits are consumed, and that replaying with the same idempotency key returns the first result without regenerating or charging. Those are exactly the behaviors an agent needs before committing to a costly, destructive mutation.

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?

Three dense sentences, front-loaded with the core action before the destructive and cost implications, with no filler. The parenthetical '(photos finish in the background; pendingAssetIds lists them)' is slightly crammed but carries real information, so the density is justified rather than wasteful.

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 13-parameter destructive generator with an output schema available, the description covers the highest-risk facts: full board replacement, project rename, credit consumption, async image completion, and idempotent replay. The remaining gap is guidance on how the required goal and expectedRevision interact with the call (e.g., what a revision mismatch does), which an agent would still have to infer.

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?

With 62% schema description coverage across 13 parameters, the schema does much of the work (style, places, sourceUrl, slideCount, imageModelId, characterIds, expectedRevision all documented inline). The description adds meaning for the idempotency key and for withImages ('optional AI photos') and style ('brand kit or a preset style'), but leaves goal, workspaceId, and the exact revision-conflict behavior unexplained, so it lands at the baseline.

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 opens with a specific verb and resource ('Write and design a full carousel from a prompt into the project board') and enumerates the produced artifacts (hook, body slides, CTA, caption, styling, optional AI photos). It implicitly separates itself from editing by stating it 'Replaces the current board and renames the project', though it never names a sibling such as carousels_board_edit to route the agent explicitly.

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?

Usage is implied rather than stated: this is the full-generation path from a prompt, versus incremental editing. The retry/idempotency sentence gives a clear condition for re-invoking the same call, but there is no explicit when-not-to-use guidance and no named alternative for partial edits, style tweaks, or template application.

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