Skip to main content
Glama

remove_video_background_media

Remove the background of a workspace video with Bria. Exports transparent WebM or ProRes MOV, with optional original audio.

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": {
      "workspaceId": "<workspaceId>",
      "mediaId": "<mediaId>"
    },
    "name": "remove_video_background_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
mediaIdYesVideo MediaDocV2 ID to process
modelIdNoBackground removal model ID. Defaults to Bria Video Remove Background.bria-video-remove-background
videoUrlNoOverride source video URL; otherwise resolves from the active media version
outputTypeNoOutput type for a compatible alternate model. Bria produces transparent video.
extraParamsNoAdditional raw V3 model parameters
workspaceIdYesThe workspace ID
outputFormatNoBria transparent video format. Defaults to WebM VP9.
preserveAudioNoKeep original audio in the Bria output. Defaults to true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / modelId / default
      Previous value: -"robust-video-matting"New value: +"bria-video-remove-background"
    • changedInput schema / properties / modelId / description
      Previous value: -"Background removal model ID. Defaults to robust-video-matting."New value: +"Background removal model ID. Defaults to Bria Video Remove Background."
    • addedInput schema / properties / outputFormat
      Added value: +{
      +  "description": "Bria transparent video format. Defaults to WebM VP9.",
      +  "enum": [
      +    "webm_vp9",
      +    "mov_proresks"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / properties / outputType / default
      Removed value: -"green-screen"
    • changedInput schema / properties / outputType / description
      Previous value: -"Replicate robust_video_matting output_type"New value: +"Output type for a compatible alternate model. Bria produces transparent video."
    • addedInput schema / properties / preserveAudio
      Added value: +{
      +  "description": "Keep original audio in the Bria output. Defaults to true.",
      +  "type": "boolean"
      +}
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose real behavior: transparent WebM or ProRes MOV output and optional retention of original audio. It omits key traits for a video-processing job — whether the call is asynchronous, whether it creates a new media document or mutates the source, and what happens on failure — which matters given siblings like get_media_statuses exist.

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?

Two sentences, zero filler, with the core action and the output characteristics front-loaded. Every clause conveys information an agent would otherwise have to infer.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter media-generation tool with a nested extraParams object, no annotations, and no output schema, the description should say more about the result — whether a job or a media ID comes back and how to poll it. It covers the output artifact well but leaves the post-call workflow and side effects unstated.

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 100%, so the baseline is 3; the description only echoes the format and audio options already documented per-parameter. It does add a small clarification that Bria itself produces transparent video while outputType applies to alternate models, but says nothing about the nested extraParams or the videoUrl override.

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?

States a specific verb and resource (remove background of a workspace video) and names the provider (Bria) plus the export formats, so the action is unambiguous. It does not, however, distinguish itself from the sibling 'remove_video_background', leaving the agent to guess why two background-removal tools exist.

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?

Usage is only implied by the phrase 'with Bria' and the format options; there is no explicit statement of when to pick this over remove_video_background or a non-Bria path, and no prerequisites or constraints are given. An agent can infer it is the transparent-video variant but must confirm by reading the schema.

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.