aseprite-ai-artist

Overview Schema Source Related Servers Discussions Admin

Reference image

reference

Import an external image as a locked, semi-transparent reference layer to trace proportions or sample colors, or extract its dominant palette without importing.

Instructions

Bring an external image into the sprite as a reference layer, so you can trace proportions or sample colours from it. Ops: 'import' (place an image on a locked, semi-transparent layer above the art), 'sample_palette' (read its dominant colours without importing), 'list', 'remove'. Importing at a different size uses nearest-neighbour; a photo scaled down to 32×32 is a starting point for a silhouette, never a finished sprite.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	No
`y`	No
`op`	Yes
`fit`	No	How to size the image against the canvas.	contain
`name`	No	Layer name. Default: 'reference'.
`path`	No	Image file to read.
`colors`	No	For 'sample_palette'.
`sprite`	No	Which sprite: its id as '#7' (what every result reports back, and the only unambiguous form — two unsaved documents are both called 'Sprite'), its filename, or its display name. Omit to use the sprite Aseprite has focused.
`opacity`	No

Output Schema

TableJSON Schema

Name	Required	Description
`op`	Yes
`layer`	No
`width`	No
`height`	No
`sprite`	Yes
`palette`	No	Dominant colours with their share of the image.
`references`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.6Sep 9, 2026

changedInput schema / properties / sprite / description

Previous value: -"Sprite filename or id. Omit to use the sprite Aseprite has focused."New value: +"Which sprite: its id as '#7' (what every result reports back, and the only unambiguous form — two unsaved documents are both called 'Sprite'), its filename, or its display name. Omit to use the sprite Aseprite has focused."

First observedv0.1.0Sep 8, 2026

TDQS

A3.9/5.0

Behavior4/5

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

The description discloses key behaviors: importing places a locked, semi-transparent layer above the art, and scaling uses nearest-neighbour. It also clarifies that a downscaled photo is not a finished sprite. These go beyond the sparse annotations (readOnlyHint=false, openWorldHint=false) and give the agent useful expectations. It does not mention side effects like overwriting existing layers, but the op list and layer description provide reasonable transparency.

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 description is concise and front-loaded with the purpose. It lists ops in a compact way and adds a practical note on scaling. It is not overly verbose, though the scaling guidance could be seen as extra, but it is valuable context. Structure is clear and scannable.

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

Completeness3/5

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

For a tool with 9 parameters and 4 distinct ops, the description is incomplete. It does not specify which parameters apply to which ops, nor does it explain return values (though an output schema exists). The scaling note is helpful but does not cover the full operational scope. Given the complexity, more detail on per-op parameter usage would be needed for an agent to call it correctly.

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

Parameters2/5

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

Schema description coverage is only 56%, and the description does not compensate. It lists ops but does not map parameters to each op (e.g., 'path' is needed for import, 'colors' for sample_palette). Parameters like 'x', 'y', and 'opacity' have no description in the schema and none in the description. The description adds little semantic value beyond what the schema already provides.

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 clear purpose: 'Bring an external image into the sprite as a reference layer'. It names the resource (sprite) and the action (import/reference), and the list of ops (import, sample_palette, list, remove) immediately distinguishes it from siblings like 'look' or 'read_pixels', which deal with viewing or reading pixels rather than managing reference images.

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 description gives practical usage context: importing at a different size uses nearest-neighbour and a scaled photo is only a silhouette starting point, not a finished sprite. However, it does not explicitly state when to prefer this tool over alternatives or when not to use it. The ops themselves imply usage, but no exclusions or comparison to sibling tools are given.

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

Deploy Server