Skip to main content
Glama

Remove Video Background

remove_video_background
Destructive

Remove or replace a video background with transparency, a solid color, or a custom image; process via file upload or public URL and retrieve results asynchronously.

Instructions

This tool will remove or replace the background of a video, producing a transparent, solid-color, or custom-image background. This is an asynchronous operation and spends credits; use get_job_status with the returned job_id to retrieve the result. It takes the following arguments: - media_file or video_url (one required): The video to process, either an uploaded file or a public URL that links directly to a real video file (not a web page). - output_transparent (bool, optional): Make the background transparent. Defaults to true unless a color or image background is given. - background_color (str, optional): Hex color to fill the background with. - background_image_url (str, optional): Public URL of an image to use as the new background. - duration_seconds (number, optional): Informational only; the server measures the real length (max 3600s) to price the job. - is_watermark (bool, optional): Defaults to true. Watermark-free exports cost double for accounts that have never purchased credits.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "remove_video_background"
  }
}

Input Schema

NameRequiredDescriptionDefault
video_urlNoPublic URL of the video to process. Use this or media_file.
media_fileNoBase64-encoded video or video data URI. Use this or video_url.
is_watermarkNoWhether the output carries the BGRemover watermark. Defaults to true. Watermark-free exports cost double for accounts that have never purchased credits.
background_colorNoHex color (e.g. '#00ff00') to fill the background with instead of transparency.
duration_secondsNoOptional and informational only: the server always measures the real video length (max 3600s), which determines the credit cost.
output_transparentNoIf true, the removed background becomes transparent. Defaults to true unless background_color or background_image_url is given.
background_image_urlNoPublic URL of an image to use as the new background. Takes precedence over background_color.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructive=true, openWorldHint=true and non-idempotent, yet the description adds real behavioral context on top: asynchronous execution, credit consumption, watermark-free exports costing double for new accounts, the 3600s server-measured cap, and precedence between background options. It omits failure/refund semantics and whether credits are consumed on a failed job, which is the main remaining behavioral gap for a paid destructive operation.

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 imperative first sentence and the async/credit callout are well front-loaded, but the bulleted parameter list duplicates text already present in a fully-described schema, making the definition longer than its informational content warrants.

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 correctly explains that the immediate result is a job_id to poll via get_job_status, and all seven parameters are accounted for. The only shortfall is lack of guidance on error/failure outcomes for a credit-spending destructive job.

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 100%, so most of the parameter bullets restate structured documentation nearly verbatim (is_watermark, duration_seconds, background_color, output_transparent). The one genuine addition is the '(one required)' mutual-exclusivity constraint between media_file and video_url, which the schema does not express via oneOf, but the rest is largely duplication, keeping this at baseline.

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 opening sentence names a specific verb and resource ('remove or replace the background of a video') and enumerates the three output modes (transparent, solid-color, custom-image), which cleanly separates it from the sibling remove_image_background and from the upload_* tools.

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 routing guidance: the operation is asynchronous, so the agent must call get_job_status with the returned job_id, and it warns the call spends credits. It does not explicitly say when to prefer this over remove_image_background or media_file over video_url beyond the '(one required)' note, so it stops short of full alternative coverage.

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