Skip to main content
Glama

Make screen scene

make_screen_scene

Show the real product: turn one of the brand's app screenshots into a short clip at the format's size, with a slow push-in or pan, inside a phone, tablet or browser frame (or full screen). 5 credits, no generation. Returns a task_id at once; the clip takes up to a minute, so follow with get_task. Its video_url goes straight into render_video as video.url.

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": {
      "format": "<format>"
    },
    "name": "make_screen_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
focusNoWhere a push-in heads, as fractions of the frame; default the middle
imageNoOr a stored screenshot (uploads/..., assets/...) or a public https image
deviceNoauto picks from the screenshot's shape: phone for tall, tablet for near-square, browser for wide. none fills the frame with the screenshot.auto
formatYes
motionNopush_in: slow move towards focus. pull_out: the reverse. pan_down / pan_up: drift down or up (a tall screenshot with device none scrolls). still: no movement.push_in
secondsNo
asset_idNoA screenshot in the brand kit (get_brand lists them). With brand_id and no asset_id or image, the kit's first screenshot.
brand_idNoA brand kit from list_brands (id or name). Brings the colours, fonts, logo, website and default copy (headline, call to action, small print); use instead of brand.
status_barNoPhone screens: true when the screenshot starts at the app's own header with no phone status bar (captured in a browser); a status bar in the header's colour goes above it, so the camera island doesn't cover the header.
caption_roomNoWhere the captions will go; the device leaves them a clear band. Default top on 9:16 (a bigger phone). Use bottom when the captions must sit at the bottom for the whole ad (joined with a lifestyle shot, say); the phone then also stays clear of the small print.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations (which only say it is not read-only and not idempotent), the description discloses the cost (5 credits), that nothing is generated, that the call is asynchronous with an immediate task_id, and that rendering can take up to a minute. That is exactly the operational context an agent needs before invoking a job-creating tool.

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 what the tool produces and followed by cost, async behavior, and chaining. Every sentence carries information, though the packed phrasing makes it slightly harder to scan than a bulleted breakdown would be.

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?

With no output schema, the description still explains the return value (task_id), the latency, and how to consume the result downstream, which covers the main ambiguity for a 10-parameter job tool. It does not address conflicting inputs such as supplying both image and asset_id, a minor remaining gap.

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 coverage is already 80%, so the schema documents focus, device, motion, status_bar, and caption_room in detail. The description only reinforces the device options (phone/tablet/browser or full screen) and the brand_id-vs-brand choice, adding little beyond the structured fields.

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 opens with a specific verb and resource: turn a brand app screenshot into a short clip at the format's size, with a push-in or pan inside a phone/tablet/browser frame. That level of detail separates it from siblings like place_screen, add_scene, and animate_image without opening any schema.

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?

It conveys when to use the tool (show the real product, not a generated one) and gives explicit next steps: follow with get_task and pass video_url into render_video as video.url. It also tells the agent to prefer brand_id over brand, but it does not contrast the tool against device/screen-placement siblings like place_screen.

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