Skip to main content
Glama

Car Background AI

Create custom background

create_background

Create a new reusable background scene for the workspace, such as the dealer's own showroom, a branded studio or a specific outdoor setting. Use it when none of the scenes in list_backgrounds fits; it does not edit a car photo (that is generate_background), and to adjust a custom background that already exists use refine_background instead of creating another. Give a description, reference_image_urls, or both; add base_background_id to start from a built-in scene and describe only what to change. Renders a preview with a demo car and returns it as an image plus the new background's id, ready to pass to generate_background. Costs one credit; a rejected or failed request is not charged.

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": "create_background"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoDisplay name. Suggested if omitted.
descriptionNoThe scene: walls, floor, lighting, setting. E.g. 'A bright showroom with light oak flooring and floor-to-ceiling windows'.
base_background_idNoA built-in background `id` to start from; the description then says what to change.
reference_image_urlsNoUp to three public image URLs of the place or style to recreate.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds substantial context beyond them: it renders a preview with a demo car, returns an image plus the new background's id, states the cost (one credit) and the billing exception (rejected or failed requests are not charged). The output value is also framed as an input to generate_background, which tells the agent how to chain calls.

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 purpose, then alternatives, then parameter rules, then cost/return behavior — a logical order with no filler. It is dense and sentence three packs several clauses together, but every sentence carries information an agent needs; nothing is redundant.

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?

There is no output schema, and the description compensates by describing the return (preview image plus the new background's id). For a zero-required-parameter creation tool, it covers trigger conditions, parameter combinations, billing, and the downstream handoff, leaving no obvious gap.

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 would be 3, but the description adds real combinatorial semantics: description, reference_image_urls, or both must be supplied, and base_background_id should be paired with a description that says only what to change. That constraint is not expressed in the schema and materially affects how an agent fills the optional parameters.

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?

Specific verb+resource ('Create a new reusable background scene for the workspace') with concrete examples of what a background is (showroom, branded studio, outdoor setting). It also explicitly names what it is not (generate_background edits car photos) and what a sibling does (refine_background for existing custom backgrounds), so an agent can distinguish it from list_backgrounds, refine_background and generate_background without opening schemas.

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 an explicit trigger ('use it when none of the scenes in list_backgrounds fits'), an explicit exclusion ('it does not edit a car photo'), and an explicit alternative for the adjacent case ('to adjust a custom background that already exists use refine_background instead of creating another'). This is the when/when-not/alternatives triad done properly.

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