Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

draw_pixels

Set individual pixels with exact coordinates and hex colors for precise detail work in Aseprite, applying a whole batch as one undo step (up to 4096 pixels per call).

Instructions

Set individual pixels: pixels is a list of {"x": int, "y": int, "color": "#rrggbb[aa]"}. The precision tool for detail work — one undo step for the whole batch. Capped at 4096 pixels per call. Headless: pass file.

preview true also returns a before/after picture of the canvas with the changed-pixel count and bbox.

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": {
      "pixels": "<pixels>"
    },
    "name": "draw_pixels"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
pixelsYes
previewNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations carry no readOnly/destructive hints, so the description carries the burden and does well: it discloses atomicity ('one undo step for the whole batch'), a hard rate/size limit (4096 pixels per call), a mode prerequisite (headless requires 'file'), and the side effect of preview returning a before/after image. It does not say what happens for out-of-range coordinates or malformed colors, which is the main remaining behavioral gap.

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?

Front-loaded with the most-needed information (the pixel payload format), then positioning, limit, mode note, and the preview behavior — no filler sentences. Slightly fragmented into short clauses, but each earns its place.

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?

With 3 parameters, an output schema present, and only a title annotation, the description covers payload format, batching limit, headless requirement, undo semantics, and the preview return. Only edge-case behavior (invalid coordinates/colors, partial failure) is left unexplained, which is minor given the output schema covers the return shape.

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

Parameters5/5

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

Schema description coverage is 0%, yet the description fully compensates: it documents the pixel dict keys, the '#rrggbb[aa]' color format with optional alpha, when to supply 'file', and what 'preview' adds to the response. Every parameter gains meaning the schema alone does not provide.

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?

Opens with a specific verb+resource ('Set individual pixels') and immediately qualifies scope with the exact pixel object shape. It also positions itself against the shape-drawing siblings ('the precision tool for detail work'), so an agent can tell it apart from draw_line or draw_circle without inspecting schemas.

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 'precision tool for detail work' framing plus the per-call cap gives a clear sense of when this tool is appropriate versus bulk/shape tools, and the headless note tells the agent it must pass 'file' in non-interactive contexts. It stops short of naming an explicit alternative or exclusion (e.g. 'for straight runs use draw_line'), so it is clear context without full when-not guidance.

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