Skip to main content
Glama

Car Background AI

Refine custom background

refine_background
Destructive

Adjust a custom background that already exists and render a new preview, e.g. after create_background when the preview is close but not right. description is only the change to make ('make the floor darker and the lighting warmer'); everything else in the scene is kept, and reference_image_urls can show the look to move towards. The background is updated in place under the same id and name, so later generate_background calls use the refined scene; photos already generated are not changed. Works on custom backgrounds only, not built-in ones; to start a different scene use create_background. Returns the new preview image. Costs one credit; a rejected or failed request is not charged.

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": {
      "background_id": "<background_id>",
      "description": "<description>"
    },
    "name": "refine_background"
  }
}

Input Schema

NameRequiredDescriptionDefault
descriptionYesWhat to change.
background_idYesThe `id` of a custom background.
reference_image_urlsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true; the description usefully bounds that destructiveness by explaining the background is updated in place under the same id and name and that already-generated photos are not changed. It also adds cost behavior (one credit, not charged on rejection/failure), which annotations cannot express. It does not cover latency or what a rejection looks like, keeping it just short of the top score.

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?

Purpose and the create_background comparison are front-loaded, and each subsequent sentence carries distinct information (in-place semantics, restriction, cost). The first sentence is somewhat run-on with the parenthetical example, but no sentence is filler.

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 stating the return value ('Returns the new preview image'), plus the mutation's blast radius, eligibility constraint, and billing behavior. For a three-parameter mutation tool this covers everything an agent needs to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 67% and the schema text is terse ('What to change'), so the description does real work: it clarifies that description is a delta ('only the change to make') with a concrete example, and that reference_image_urls conveys the target look rather than being source content. This meaning is unavailable from the schema alone.

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: 'Adjust a custom background that already exists and render a new preview'. It immediately distinguishes itself from the sibling create_background by scoping to existing custom backgrounds and describing the delta-based edit model.

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 ('e.g. after create_background when the preview is close but not right'), an explicit exclusion ('Works on custom backgrounds only, not built-in ones'), and names the alternative for the other case ('to start a different scene use create_background'). Nothing is left to inference.

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