Skip to main content
Glama
Brilliant MCP

Brilliant MCP

Official

add_cutout_outline

Traces the visible edge of a background-removed image into a stroke-only vector outline placed above the cutout for a sticker-style border. Returns the new outline ID per image.

Instructions

Add an outline around the subject of an image whose background was removed (remove_background first): the cutout's visible edge is traced into a new vector element placed directly above the image, aligned with its crop, rotation, flip and scale; stroke only, no fill, outside stroke, round joins (the sticker look). The outline is an ordinary element afterwards (restyle, move or delete it). ids: the image element ids (or #refs; a frame, group or instance id reaches the cut images inside it). color: optional #RRGGBB stroke color (default plain white). width: optional stroke width in px (default 2 percent of the image's short edge). Answers the new outline id per image, or the honest refusal (no removed background, nothing visible to trace, a tiled image). Runs locally: no Brilliant AI usage.

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": "add_cutout_outline"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYesElement IDs (or #refs) of images whose background was removed. Required.
colorNoStroke color #RRGGBB. Optional.
widthNoStroke width in px. Optional.
canvasIdYesCanvas ID. Required.
sessionIdNoSession ID from init. Optional.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4.4/5.0
Behavior4/5

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

Annotations say readOnlyHint=false, destructiveHint=false, idempotentHint=false but disclose nothing about the outcome; the description fills that gap with geometry (aligned with crop, rotation, flip and scale), style (stroke only, outside stroke, round joins), lifecycle ('an ordinary element afterwards – restyle, move or delete it'), and refusal behavior. The one omission is that each call adds a new element, which explains the non-idempotent hint but is only implied by 'new vector element'.

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?

A single dense paragraph, but front-loaded with the purpose and prerequisite before geometry, parameters and returns. Nearly every clause carries information; the parenthetical 'the sticker look' and the 'honest refusal' aside are the only mildly decorative bits.

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?

With no output schema, the description correctly states the return value (new outline id per image) and the failure responses, plus execution locality ('Runs locally: no Brilliant AI usage'). Combined with parameter defaults and the sibling prerequisite, an agent can call this correctly without further information.

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 earns more: it discloses that a frame, group or instance id reaches the cut images inside, and it supplies defaults the schema omits ('default plain white', 'default 2 percent of the image's short edge'). Those defaults materially change what the agent passes.

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 ('Add an outline around the subject of an image whose background was removed') and names the prerequisite sibling (remove_background) so the agent can sequence tools. The result ('a new vector element placed directly above the image') further pins down what the tool produces, distinguishing it from vectorize_image and create_modify_elements.

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

Usage Guidelines4/5

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

The prerequisite 'remove_background first' is an explicit gating condition, and the refusal cases ('no removed background, nothing visible to trace, a tiled image') tell the agent when the tool will not apply. It stops short of naming a full alternative workflow for non-cutout images, so it is clear context rather than complete when/when-not routing.

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