Skip to main content
Glama
Brilliant MCP

Brilliant MCP

Official

remove_background

Cuts the background from real photos on the canvas, keeping the subject’s exact pixels and making the background transparent in place. Use it to cut out real images without regenerating them.

Instructions

Remove the background from real photos on the canvas: the subject keeps its exact pixels (the real face, the real product) and the background becomes transparent, in place, in the same image fill (crop, scale mode and opacity kept). Use it instead of generate_image whenever the image is a real photo and the user wants it cut out: "a real photo, keep the pixels, cut the background". generate_image regenerates the picture and invents new pixels. ids: the element ids (or #refs) whose image fills to cut (a frame, group or instance id reaches every image inside it); one request per distinct image. A cut fill reads back as img(, ..., src()); execute_commands restore_background puts the original back. Answers the new asset path per element, or the named failure (no subject, allowance used, lane unavailable, image missing). add_cutout_outline then traces an outline around the cut subject. Runs on Brilliant AI: a signed-in account's Brilliant AI usage; in the built-in chat, a signed-out user gets the free daily cutouts of the /remove-background page with no account, and is told when they are used up.

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": {
      "canvasId": "<canvasId>",
      "ids": "<ids>"
    },
    "name": "remove_background"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYesElement IDs (or #refs) holding the image fills to cut; a frame, group or instance id cuts every image inside it. Required.
canvasIdYesCanvas ID. Required.
sessionIdNoSession ID from init. Optional.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say this is a non-read-only, non-destructive, open-world, non-idempotent call. The description goes well beyond that: the edit is in place within the existing image fill with crop, scale mode and opacity preserved, the cut fill reads back in a specific pattern, restore_background reverts it, and named failure modes (no subject, allowance used, lane unavailable, image missing) are listed. It even discloses the account/allowance model, including the signed-out free daily cutouts.

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 generate_image contrast are front-loaded, and nearly every clause carries information (id scoping, reversal, failure names, auth). The final sentence about Brilliant AI allowances is a dense run-on that could be split, 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?

For a mutating tool with no output schema, the definition covers what changes, what is preserved, how to reverse it, what it returns per element, what failures look like, and the auth/allowance context. Nothing an agent needs to call it correctly is missing.

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. The description still adds meaning: it clarifies that a frame, group or instance id reaches every image inside it, and adds the operational constraint of "one request per distinct image" that is absent from the schema.

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 description opens with a specific verb and resource ("Remove the background from real photos on the canvas") and immediately states the key outcome: subject pixels are preserved, background becomes transparent. It explicitly contrasts itself with the sibling generate_image, so the agent can pick the right tool without comparing 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?

Usage is stated as a decision rule: "Use it instead of generate_image whenever the image is a real photo and the user wants it cut out," with a concrete reproduction quote, plus the inverse case (generate_image regenerates and invents pixels). It also names add_cutout_outline as the natural follow-up and execute_commands restore_background as the undo path.

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