Skip to main content
Glama
Sign In

CartViral

by com.cartviral
OverviewDiscussionsAdmin

Edit a real video: swap or add anything

edit_video

Change one thing in a real video and keep everything else: the product from a photo in someone's hand instead of what they hold, one can swapped for another, a bottle put on the desk, a car driving past. The first 10 s are used; the people, motion, camera, light and the video's own sound stay. Name the photos photo1.jpg, photo2.jpg in the prompt in the order given, and say what happens to things around the swapped object (e.g. "and remove the earbuds"). 2 credits. Poll list_creations.

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": {
      "video": "<video>",
      "prompt": "<prompt>"
    },
    "name": "edit_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
videoYesThe video to edit (mp4, webm or mov): a CartViral /u/ link, or any public https link to the file (downloaded once)
aspectNoFrame: 9:16 vertical (TikTok, Reels, Shorts), 4:5, 1:1, 16:9 (YouTube, covers, banners)9:16
promptYesWhat changes, e.g. "replace the cup in her hand with the tumbler from photo1.jpg"
product_imagesNoPhotos of the product or object to put in, referred to as photo1.jpg, photo2.jpg: CartViral /u/ links or public https file links, up to 5

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare the generic write/open-world/non-idempotent profile, while the description discloses far more: only the first 10 s are used, people/motion/camera/light/original audio are preserved, and each call costs 2 credits. Those are exactly the facts an agent needs before spending credits on a 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?

Front-loaded with the core behavior, followed by constraints, credit cost and the polling hint — little waste. The middle sentences are long and packed, but each carries operative detail rather than filler.

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?

No output schema exists, and the description compensates by naming list_creations as the results endpoint and stating cost and the 10 s truncation limit. It does not say what identifier the call returns or what failure looks like, which is the remaining small gap for a 4-parameter asynchronous generation tool.

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?

Schema coverage is 100%, so baseline is 3; the description still adds a convention the schema does not state — that product_images must be referenced as photo1.jpg, photo2.jpg and that the ordering in the prompt matters. It also nudges the agent to describe removals of adjacent objects in the prompt.

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?

States a specific verb and resource ("Change one thing in a real video and keep everything else") with concrete examples of the swap operation. That framing distinguishes it cleanly from siblings like reframe_video, copy_motion and breakdown_video, which do not edit content in place.

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?

Gives clear operating context: use it for single-object swaps/additions, name photos photo1.jpg/photo2.jpg in prompt order, and describe what happens to surrounding objects. It also closes the loop with "Poll list_creations." It stops short of explicitly excluding alternatives (e.g. when to prefer reframe_video or remake_from_reference).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All CartViral toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources