Skip to main content
Glama

pixel_import

Idempotent

Import native-resolution PNG pixel art or sprite sheets as editable recipes without altering pixels; slice by atlas or frame and save as a revision.

Instructions

Turn existing pixel art or a sprite sheet PNG into an editable recipe. Import a native-resolution PNG (RGB, RGBA, greyscale or indexed, up to 8 bits per channel; a sprite sheet sliced by its unscaled atlas, or by frame, the size of one frame) as an editable recipe without changing any pixel. Pass data (base64 PNG) or path (inside the server root). Saves the recipe as a revision.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pixel_import"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNoBase64 PNG bytes.
nameNo
pathNoPNG file path relative to the server root.
atlasNo
frameNoA sheet with no atlas: the size of one frame, such as "24x24".
paddingNoWith frame: the empty border round each frame; found when left out.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.15.0
    • addedInput schema / properties / frame
      Added value: +{
      +  "description": "A sheet with no atlas: the size of one frame, such as \"24x24\".",
      +  "type": "string"
      +}
    • addedInput schema / properties / padding
      Added value: +{
      +  "description": "With frame: the empty border round each frame; found when left out.",
      +  "maximum": 64,
      +  "minimum": 0,
      +  "type": "integer"
      +}
  2. First observedv0.9.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false. The description adds real context beyond them: the import is pixel-exact, it accepts RGB/RGBA/greyscale/indexed up to 8 bits per channel, and it has the side effect of saving a new revision.

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?

Purpose is front-loaded and every clause carries format or slicing information. It is somewhat dense and repeats 'editable recipe' and 'PNG' across the first two sentences, but nothing is truly wasted.

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 6-parameter mutation tool with no output schema, the description covers inputs and the revision side effect well but never says what is returned (e.g. a recipe identifier or revision number) and leaves the name parameter undocumented.

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 67% schema coverage the baseline is 3, but the description goes further: it explains data as base64 PNG, path as relative to the server root, the atlas-vs-frame choice for sheet slicing, and that padding is auto-detected when omitted. The name parameter is left unexplained in both places.

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 resource: turn a native-resolution PNG into an editable recipe without altering pixels. That is clearly distinct from pixel_compile, pixel_render or pixel_validate, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

It implies the use case (you already have pixel art or a sprite sheet) and tells you to pass either data or path, plus when to use atlas vs frame. It does not say when to prefer this over other import-adjacent workflows or what preconditions exist, so the guidance is contextual rather than explicit.

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