Skip to main content
Glama

Car Background AI

Replace photo background

generate_background

Replace the background of one car photo with a chosen scene: the main tool for turning a phone photo into a listing photo. The car is kept as photographed and gets shadows, lighting and reflections that match the scene. Works on exterior, interior and detail shots. Pick background_id with list_backgrounds first and use the same one for every photo of a car. In the same call it can hide the plate (hide_license_plate, with license_plate_style and, for logo, a license_plate_logo from list_logos), draw a dealer logo, reframe to an aspect_ratio, centre the car or show it washed. To hide the plate without changing the background use hide_license_plates; to make a new scene use create_background. One photo per call; the source photo is not modified. Costs one credit, and a failed generation is not charged. Can take up to a minute. Returns a signed image_url of the high-resolution result, valid for 7 days.

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": {
      "image_url": "<image_url>",
      "background_id": "<background_id>"
    },
    "name": "generate_background"
  }
}

Input Schema

NameRequiredDescriptionDefault
logoNoDraw one of the workspace's logos on the result.
clean_carNoExperimental: show the car freshly washed.
image_urlYesPublic HTTPS URL of the car photo (JPEG, PNG or WebP).
center_carNoExperimental: centre, enlarge and level the car like a listing photo.
aspect_ratioNoOutput aspect ratio. Omit to keep the photo's own.
background_idYesA background `id` from list_backgrounds.
hide_license_plateNoHide a legible license plate (exterior photos).
license_plate_logoNoRequired with license_plate_style `logo`.
license_plate_styleNoWith hide_license_plate: `plain` (default) replaces it with a blank plate, `blur` blurs it, `logo` shows the dealer's plate logo (set license_plate_logo).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Goes well past the annotations (readOnly/openWorld/destructive): it discloses that the source photo is not modified, that the call costs one credit, that a failed generation is not charged, that it can take up to a minute, and that the returned signed image_url is valid for 7 days. Those are exactly the operational facts an agent needs before invoking.

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?

Purpose is front-loaded in the first clause, followed by what is preserved, then workflow, then side capabilities, then cost/latency/return. Dense but every clause carries decision-relevant information; no filler sentences.

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

Completeness5/5

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

Covers the full picture for a 9-parameter generative tool: inputs sourcing, combined behaviors, mutation scope over the source, cost, failure billing, latency, and return value format and lifetime. Nothing material is left for the agent to guess.

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 the baseline is 3, but the description adds cross-tool meaning the schema cannot: where background_id comes from, that the same one should be reused per car, and the dependency between hide_license_plate, license_plate_style and a plate-type logo from list_logos. It also flags logo, aspect_ratio, center_car and clean_car as combinable in the same call.

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 ('replace the background of one car photo with a chosen scene') and explicitly positions itself as 'the main tool for turning a phone photo into a listing photo', which separates it from create_background, refine_background and hide_license_plates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit workflow ordering ('Pick background_id with list_backgrounds first', 'use the same one for every photo of a car') and names the alternatives with the condition that selects them: hide_license_plates for plate-only hiding, create_background for a brand-new scene. It also states the one-photo-per-call constraint.

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