Skip to main content
Glama

ChatGPT conversation video

create_chatgpt_conversation

Create a ChatGPT conversation animation. An assistant turn's imageUrl is a generated image (blurred, then revealed, imagePosition before / after the text); a user turn's imageUrl is a photo attached to the message, shown above it. keyboard shows the on-screen keyboard while the user types (auto, the default), always, or never. All options controllable. Images: every image field takes an https URL from an allowed host (see /integrations), or upload:<short-label> (e.g. upload:contact-avatar) when the user wants to use their own image — including one attached to this chat, which cannot be passed to tools. Never ask the user to host an image somewhere: the returned link asks them to add each upload: image from their device before it exports. Use the same label for the same image and a different label for a different one. Free-plan exports include a MockClip watermark and the free plan includes 2 MCP renders; if the caller is on the free plan, mention that they can upgrade at /pricing for watermark-free exports and more renders.

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": {
      "messages": "<messages>"
    },
    "name": "create_chatgpt_conversation"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo
themeNo
sceneIdNoStage the clip on a scene instead of a flat frame. Overrides videoFormat and showBezel: the export takes the scene's aspect. Two kinds. 3D close-up — a 3D phone filmed by a camera that flies in close to each new message, card or banner as it appears, with depth of field and motion blur: "closeup" (9:16), "closeup-wide" (16:9). Hand-held — the clip composited onto real footage of a hand holding a phone, for a filmed look; vertical 9:16: "outdoors" (outdoors), "bookshelf" (bookshelf), "two-hands" (two hands), "on-desk" (on the desk), "dim-room" (dim room); landscape 16:9 (YouTube, presentations): "city-wide" (city), "desk-wide" (desk), "neon-wide" (neon), "studio-wide" (studio). Default: none.
keyboardNo
messagesYes
incognitoNo
showBezelNoDraw the iPhone bezel around the screen (default true). With 1:1 it frames the top of the phone; false gives a plain frame.
textScaleNoText size: a zoom of the phone UI (text, bubbles, avatars, bars, keyboard, notification banners) as a multiplier from 1 (default, the app's real size) to 1.5, in steps of 0.1 — use it when a short conversation or a single notification should fill the screen. Chat and notification apps only; the other apps ignore it.
showWelcomeNo
videoFormatNoOutput aspect ratio. "1:1" is a square for feed posts: chat apps fit the conversation into the square, the other apps show the top of the screen (phone-call ignores it). "9:16", "9:19.5" (iPhone) and "3:2" apply with showBezel false. "16:9" (widescreen) is for the notification tools with background.backgroundType "floating" only, where the frame is a photo scene and any aspect ratio applies without a bezel; on any other clip it is ignored. Default: the iPhone bezel, 9:16.
welcomeTextNo
exportFormatNoOutput file. "mp4" (default) and "gif" are opaque. "webm" (VP9) and "mov" (ProRes 4444, large files) keep an alpha channel: the only way a transparent background, or the corners around the phone bezel, stay transparent. With background.backgroundType "transparent" and no exportFormat the clip exports as webm. Transparent WebM / MOV export needs a Creator or Studio plan; on other plans the clip is made as mp4 and the reply says so.
headerBannerNo
exportQualityNoResolution and frame rate of the file: "720p" or "1080p" (Full HD) at 15, 24, 30 or 60 fps, e.g. "1080p-30". Default "720p-30". Full HD takes up to 4× as long to export; 60 fps about twice as long and needs a Creator or Studio plan — on other plans the clip is made at 30 fps and the reply says so.
showStatusBarNoDraw the iOS status bar (time, signal, battery) at the top of the screen (default true). Applies with showBezel false or a sceneId: inside the iPhone bezel the status bar is always drawn, so to remove it set showBezel false too.
soundSettingsNo
sceneBackgroundNoBackdrop behind the phone on a 3D close-up scene (sceneId "closeup" / "closeup-wide"): a colour as "#RRGGBB" — the backdrop is a soft gradient made from it, so a brand colour or a dark one both work — or "transparent" for the phone alone over an alpha channel, to lay over other footage (the clip then exports as webm unless exportFormat says otherwise; mp4 and gif cannot carry it and get the default backdrop). Default: a light blue. Ignored without a 3D close-up scene.
showQuickActionsNo
showHomeIndicatorNoDraw the iOS home indicator bar at the bottom of the screen (default true).
keepWelcomeVisibleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / sceneBackground
      Added value: +{
      +  "description": "Backdrop behind the phone on a 3D close-up scene (sceneId \"closeup\" / \"closeup-wide\"): a colour as \"#RRGGBB\" — the backdrop is a soft gradient made from it, so a brand colour or a dark one both work — or \"transparent\" for the phone alone over an alpha channel, to lay over other footage (the clip then exports as webm unless exportFormat says otherwise; mp4 and gif cannot carry it and get the default backdrop). Default: a light blue. Ignored without a 3D close-up scene.",
      +  "pattern": "^(transparent|#[0-9a-fA-F]{6})$",
      +  "type": "string"
      +}
  2. Changed4 schema fields changed
    • changedInput schema / properties / sceneId / description
      Previous value: -"Composite the clip onto real footage of a hand holding a phone, for a filmed look. Overrides videoFormat and showBezel: the export takes the scene's aspect, with the footage around the phone. Vertical 9:16 scenes: \"outdoors\" (outdoors), \"bookshelf\" (bookshelf), \"two-hands\" (two hands), \"on-desk\" (on the desk), \"dim-room\" (dim room). Landscape 16:9 scenes (YouTube, presentations): \"city-wide\" (city), \"desk-wide\" (desk), \"neon-wide\" (neon), \"studio-wide\" (studio). Default: none."New value: +"Stage the clip on a scene instead of a flat frame. Overrides videoFormat and showBezel: the export takes the scene's aspect. Two kinds. 3D close-up — a 3D phone filmed by a camera that flies in close to each new message, card or banner as it appears, with depth of field and motion blur: \"closeup\" (9:16), \"closeup-wide\" (16:9). Hand-held — the clip composited onto real footage of a hand holding a phone, for a filmed look; vertical 9:16: \"outdoors\" (outdoors), \"bookshelf\" (bookshelf), \"two-hands\" (two hands), \"on-desk\" (on the desk), \"dim-room\" (dim room); landscape 16:9 (YouTube, presentations): \"city-wide\" (city), \"desk-wide\" (desk), \"neon-wide\" (neon), \"studio-wide\" (studio). Default: none."
    • changedInput schema / properties / sceneId / enum
      Previous value: -[
      -  "outdoors",
      -  "bookshelf",
      -  "two-hands",
      -  "on-desk",
      -  "dim-room",
      -  "city-wide",
      -  "desk-wide",
      -  "neon-wide",
      -  "studio-wide"
      -]New value: +[
      +  "closeup",
      +  "closeup-wide",
      +  "outdoors",
      +  "bookshelf",
      +  "two-hands",
      +  "on-desk",
      +  "dim-room",
      +  "city-wide",
      +  "desk-wide",
      +  "neon-wide",
      +  "studio-wide"
      +]
    • changedInput schema / properties / videoFormat / description
      Previous value: -"Output aspect ratio. \"1:1\" is a square for feed posts: chat apps fit the conversation into the square, the other apps show the top of the screen (phone-call ignores it). \"9:16\", \"9:19.5\" (iPhone) and \"3:2\" apply with showBezel false. Default: the iPhone bezel, 9:16."New value: +"Output aspect ratio. \"1:1\" is a square for feed posts: chat apps fit the conversation into the square, the other apps show the top of the screen (phone-call ignores it). \"9:16\", \"9:19.5\" (iPhone) and \"3:2\" apply with showBezel false. \"16:9\" (widescreen) is for the notification tools with background.backgroundType \"floating\" only, where the frame is a photo scene and any aspect ratio applies without a bezel; on any other clip it is ignored. Default: the iPhone bezel, 9:16."
    • changedInput schema / properties / videoFormat / enum
      Previous value: -[
      -  "9:16",
      -  "9:19.5",
      -  "3:2",
      -  "1:1"
      -]New value: +[
      +  "9:16",
      +  "9:19.5",
      +  "3:2",
      +  "1:1",
      +  "16:9"
      +]
  3. Changed1 schema field changed
    • addedInput schema / properties / textScale
      Added value: +{
      +  "description": "Text size: a zoom of the phone UI (text, bubbles, avatars, bars, keyboard, notification banners) as a multiplier from 1 (default, the app's real size) to 1.5, in steps of 0.1 — use it when a short conversation or a single notification should fill the screen. Chat and notification apps only; the other apps ignore it.",
      +  "maximum": 1.5,
      +  "minimum": 1,
      +  "type": "number"
      +}
  4. Changed3 schema fields changed
    • addedInput schema / properties / exportQuality
      Added value: +{
      +  "description": "Resolution and frame rate of the file: \"720p\" or \"1080p\" (Full HD) at 15, 24, 30 or 60 fps, e.g. \"1080p-30\". Default \"720p-30\". Full HD takes up to 4× as long to export; 60 fps about twice as long and needs a Creator or Studio plan — on other plans the clip is made at 30 fps and the reply says so.",
      +  "enum": [
      +    "720p-15",
      +    "720p-24",
      +    "720p-30",
      +    "720p-60",
      +    "1080p-15",
      +    "1080p-24",
      +    "1080p-30",
      +    "1080p-60"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / showHomeIndicator
      Added value: +{
      +  "description": "Draw the iOS home indicator bar at the bottom of the screen (default true).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / showStatusBar
      Added value: +{
      +  "description": "Draw the iOS status bar (time, signal, battery) at the top of the screen (default true). Applies with showBezel false or a sceneId: inside the iPhone bezel the status bar is always drawn, so to remove it set showBezel false too.",
      +  "type": "boolean"
      +}
  5. Changed1 schema field changed
    • addedInput schema / properties / exportFormat
      Added value: +{
      +  "description": "Output file. \"mp4\" (default) and \"gif\" are opaque. \"webm\" (VP9) and \"mov\" (ProRes 4444, large files) keep an alpha channel: the only way a transparent background, or the corners around the phone bezel, stay transparent. With background.backgroundType \"transparent\" and no exportFormat the clip exports as webm. Transparent WebM / MOV export needs a Creator or Studio plan; on other plans the clip is made as mp4 and the reply says so.",
      +  "enum": [
      +    "mp4",
      +    "gif",
      +    "webm",
      +    "mov"
      +  ],
      +  "type": "string"
      +}
  6. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare that this writes and is non-destructive, non-idempotent and closed-world. The description adds the traits that actually matter: free-plan exports carry a MockClip watermark and only 2 MCP renders, plan-gated features (transparent webm, 60 fps) are silently downgraded with an explanation in the reply, and `upload:` links require the user to attach files from their device before export.

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, then image handling, then keyboard, then plan/watermark caveats — a sensible order with little filler. Some sentences are dense and run long (the image paragraph especially), but nothing is clearly redundant given the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 20-parameter nested animation builder with no output schema, the description covers the highest-risk areas: the image pipeline, the upload-label contract, plan-based downgrades, and watermark disclosure. Parameter-level details for the simpler toggles are already handled by schema descriptions.

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 only 45% across 20 nested parameters, but the description adds genuine meaning for the most ambiguous ones: `imageUrl` behaves differently for assistant turns (generated, blurred then revealed) versus user turns (attached photo), and `keyboard` defaults to auto. The remaining parameters (model, theme, incognito, showWelcome, showQuickActions, soundSettings, etc.) get no explanation here, so it only partially compensates for the coverage gap.

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 first sentence gives a specific verb and resource: "Create a ChatGPT conversation animation." Combined with the sibling set (copilot, gemini, grok, imessage conversations), an agent can immediately distinguish which product conversation this creates.

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?

The description gives concrete operating guidance: use `upload:<short-label>` when the user wants their own image, never ask the user to host an image, reuse the same label for the same image, and mention the upgrade path for free-plan callers. It does not explicitly name when to choose this tool over a sibling conversation tool, so it falls short of a 5.

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