Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

add_rim_light

Adds a rim light to a layer’s edge pixels facing a chosen light position, creating a new editable layer above the art. Set color, width, radius, and frames.

Instructions

Pick out the edge of layer that faces a light: a sunset behind a figure, a fire beside a tree. light is where the light is, [x, y], and may be off the canvas for a far-off sun. Edge pixels facing it turn color; width 2 adds a dithered second row mixed with the art's own colour. With radius the light fades out that far from its source, for a fire. The rim goes on a new layer named like "Knight (rim)" just above layer, so the art is untouched and the light can be hidden or recoloured. Runs on every frame, or the active one with all_frames false. One undo step. Headless: pass file.

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": {
      "layer": "<layer>",
      "light": "<light>"
    },
    "name": "add_rim_light"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
colorNo#ffb070
layerYes
lightYes
widthNo
radiusNo
all_framesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4/5.0
Behavior4/5

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

Annotations provide only a title, so the description carries the full burden and does substantial work: it discloses that the rim lands on a NEW layer named like "Knight (rim)" just above `layer`, that the original art is untouched, that the result is one undo step, and that it processes every frame unless `all_frames` is false. What it leaves murky is the `file` argument ("Headless: pass `file`" never says whether that is an output path or a target document) and any failure behavior when `layer` does not exist.

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?

The effect and its mental model are front-loaded, then parameters, then side effects (new layer, undo, frame scope, headless). Nearly every clause adds information, though the narrative prose style and line-wrapped fragments make it slightly longer than needed for a seven-parameter tool.

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

Completeness4/5

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

For a mutation tool with no behavioral annotations and no output schema, the definition covers the important ground: what is produced, where it is placed, non-destructiveness, undo granularity, and frame scope. It omits what the call returns and the meaning of `file`, which are the remaining holes an agent would want filled.

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?

With 0% schema description coverage, the description must define all seven parameters and it largely does: `light` as `[x, y]` that may sit off-canvas, `color` as the rim tint, `width` 2 as a dithered second row mixed with the art's own colour, `radius` as a falloff distance, and `all_frames` as the per-frame toggle. Gaps remain on `color` format (hex is only visible in the schema default) and on how `layer` is matched by name, and `file` is mentioned without explanation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and effect: it picks the edge of `layer` facing a light and recolours those pixels, with concrete motivating cases ("a sunset behind a figure, a fire beside a tree"). That distinguishes it from a generic glow or outline at a conceptual level, but it never names or contrasts a sibling tool, so an agent comparing add_rim_light against add_glow or add_outline must infer the difference.

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 two example scenarios (sunset behind a figure, fire beside a tree) give a clear sense of when this effect applies, and the `radius` note ("for a fire") ties a parameter choice to a use case. It offers no explicit when-not guidance or named alternative, which is the only thing separating it from a 5.

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

Deploy Server

Other Tools