Skip to main content
Glama

Gmail inbox video

create_gmail_inbox

Create a Gmail inbox animation (new emails sliding in at the top of the inbox, unread emails in bold until they are opened, opening an email, stars, importance markers, a reply typed into the thread, an on-screen keyboard that slides up while you type). emails is the inbox, top first: each row shows senderName (on a monogram disc — monogram letter, avatarColor palette index or hex — or senderAvatarUrl), time, subject and the one-line preview; unread rows are bold; starred / important set the markers. body, to (default "to me") and label (the chip, default "Inbox") are what the email screen shows. incoming emails arrive during the clip. script plays in order: arrive (the next incoming email — or id — slides in at the top, unread, with a sound), open (tap the row with that id: the email screen slides in and the email is read from then on), star (a row's star on the inbox — id, default the top row — or the open email's), important (the open email's marker), reply (text typed on the keyboard into a draft under the email — typingSpeed chars/s, default 16 — then sent), back (to the inbox, the row now read) and pause (seconds); each step waits delayBefore seconds first. Ids default to m1, m2… for emails and n1, n2… for incoming. myName / myAvatarUrl is the account owner (replies, the search bar's disc). keyboard auto / always / never; showTaps (default true) draws a touch indicator before each tap. 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": {
      "emails": "<emails>"
    },
    "name": "create_gmail_inbox"
  }
}

Input Schema

NameRequiredDescriptionDefault
themeNo
emailsYes
myNameNo
scriptNo
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.
incomingNo
keyboardNo
showTapsNo
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.
myAvatarUrlNo
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.
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.
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.
showHomeIndicatorNoDraw the iOS home indicator bar at the bottom of the screen (default true).

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. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only say this is a non-read-only, non-destructive, non-idempotent, closed-world operation, so the description carries most of the burden and does add real behaviour: free-plan exports carry a MockClip watermark, the free plan caps MCP renders at 2, and the returned link asks the user to add each `upload:` image from their device before export. What it omits is operational behaviour an agent would want — whether the render is synchronous, how long it takes, or what the returned link looks like — so it falls short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but everything after it runs together as one dense block in which row-field documentation, script-step semantics, image-hosting policy, and free-plan marketing are interleaved with no separation. Almost every sentence carries information, yet the nesting of parentheticals and the pivot into plan/watermark advice make it hard to scan for a single parameter.

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 complex, 18-parameter nested generator with no output schema, the description covers the domain model an agent must populate: the inbox list, the incoming queue, the ordered script, the account owner, and the keyboard/tap toggles. Image sourcing and plan gating are covered too. Missing is any statement of what the call actually returns or how the export lifecycle works, which is the main residual gap at this complexity.

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 18 parameters, nested objects, and only 50% schema description coverage, the description does substantial work: it explains the inbox row anatomy field by field, says `emails` is top-first, defines each `script` step type and its effect in order, and supplies defaults the schema lacks — ids defaulting to m1/m2… and n1/n2…, `to` defaulting to "to me", `label` to "Inbox", `typingSpeed` to 16, and `delayBefore` applying before each step. Several top-level parameters (theme, soundSettings, showHomeIndicator) get no mention, but their schema entries are self-documenting.

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 opening clause names a specific verb and resource ("Create a Gmail inbox animation") and immediately enumerates what is depicted: emails sliding in, unread bold, opening, stars, reply typing, on-screen keyboard. That is far more specific than a tautology. It stops short of a 5 because it never relates itself to the many neighbouring conversation/notification tools, so routing relies on the agent reading the app name rather than on stated differentiation.

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?

There is no explicit "use this when…" or when-not statement, and no named alternative for a plain Gmail thread versus a generic chat or notification clip. What guidance exists is procedural rather than selectional: how to handle `upload:` labels, the instruction never to ask the user to host images, and the note to mention upgrading when the caller is on the free plan. Useful, but the agent still has to infer the choice of tool.

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