Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

add_reference_image

Add a reference image as a faded, locked layer over every frame of the sprite without disturbing the active drawing layer. Adjust opacity and fit, then hide or delete the layer when done.

Instructions

Put a sketch or reference on a faded, locked layer on top of the sprite, across every frame, and keep the active layer as it was, so drawing lands on the art. image_path is a file on disk; a picture pasted into chat needs saving first. fit shrinks a larger image to the canvas. opacity is 0-255. Hide or delete the layer when done. Saving to a flat format would merge it in, so hide it first. 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": {
      "image_path": "<image_path>"
    },
    "name": "add_reference_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
fitNo
fileNo
opacityNo
image_pathYes
layer_nameNoReference

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.3/5.0
Behavior5/5

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

With only a title annotation, the description carries the full burden and delivers: the layer is locked and faded, it is created across every frame, the active layer is unchanged, the operation is a single undo step, and a flat-format save would merge the reference into the art unless it is hidden first. It also discloses the headless path via the file parameter.

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 core action and its frame-wide, layer-preserving behavior are front-loaded, and each later sentence adds a distinct operational fact. The prose is somewhat run-on and mixes parameter notes with warnings, but there is no 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 five-parameter mutation tool with no annotations and no output schema, the description supplies the mutation's scope, its undo footprint, cleanup guidance, a format-related data-loss warning, and headless usage. Only the layer_name default is undocumented, which is minor.

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 description coverage is 0%, so the description must compensate, and it explains image_path (a file on disk), fit (downscales oversized images to the canvas), opacity (0-255 range) and file (headless mode). The layer_name parameter is left unexplained, a modest gap at 4 of 5 parameters covered.

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 names a specific verb and resource (put a reference image on a dedicated locked layer) and spells out the key effect: it spans every frame while the active layer is preserved so drawing still lands on the art. That implicitly separates it from import_image_as_layer, but no sibling is named explicitly, which keeps it just short of a 5.

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?

Usage context is clear: it is for tracing/drawing over a sketch, and the description tells the agent to hide or delete the layer when finished, plus that images pasted into chat must be saved to disk first. It gives no explicit named alternative (e.g. import_image_as_layer) for the case where the image should be real artwork.

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