Skip to main content
Glama

Zapmatte Green Screen Remover

create_upload

Screen a video and get a one-time upload URL. Send its duration, size, width, height and 1-4 JPEG frames (raw base64, no data URL, each up to 300 KB) sampled across the clip for content moderation. Then PUT the video bytes to putUrl with the returned contentType, and pass key as uploadKey to remove_green_screen. Requires a key.

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": {
      "fileName": "<fileName>",
      "sizeBytes": "<sizeBytes>",
      "durationSeconds": "<durationSeconds>",
      "width": "<width>",
      "height": "<height>",
      "frames": "<frames>"
    },
    "name": "create_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
widthYes
framesYesJPEG frames as raw base64.
heightYes
fileNameYesOriginal file name, e.g. clip.mp4 (the extension sets the format).
sizeBytesYes
durationSecondsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare it is a non-read-only, open-world, non-idempotent, non-destructive call; the description adds real context beyond that: the URL is one-time, the frames exist for content moderation screening, and a key is required. It also names the returned fields (putUrl, contentType, key), which matters since there is no output schema. It stops short of describing what happens when screening rejects a clip or whether keys expire.

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

Conciseness5/5

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

Three tight sentences: purpose, what to send, then what to do with the response. Front-loaded and free of filler; every clause carries operational meaning.

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 six-parameter, no-output-schema mutation tool, the description supplies the full two-step workflow and the shape of the response. The main remaining gap is failure behavior, such as what a failed moderation screen returns or how long the one-time URL and key stay valid.

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 only 33%, so the description carries the burden for duration, size, width and height, which it does by tying them to the moderation payload. It also adds format semantics for frames (raw base64, no data URL, 1-4 frames sampled across the clip, ~300 KB each) that decode the schema's opaque pattern/maxLength limits. fileName is left entirely to the schema, so it is good compensation but not complete.

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 names a specific verb pair and resource: screen a video and obtain a one-time upload URL. It is immediately distinguishable from siblings like remove_green_screen, which the description explicitly positions as the downstream step.

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 lays out the call order: invoke this, PUT the bytes to putUrl with the returned contentType, then pass key as uploadKey to remove_green_screen. That is clear routing to the next tool, but it does not state any condition under which this tool should be skipped (e.g. re-uploading an already-screened clip).

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