Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

extend_scene

Expand a canvas by specified margins and fill new space with sampled texture patches from the active layer, matching adjacent pixels so no new colors appear.

Instructions

Grow the canvas by left/right/top/bottom pixels and fill the new space on layer (the active one) by continuing its own texture, like turning a portrait scene into a wide banner. Patches of patch pixels are copied from the sample_* area (all of the layer by default) and matched to what is already beside them, so no new colours appear. Pick a sample of pure background, like open meadow, so the subject isn't copied, and big enough not to repeat. The margins come from frame and are shared by the layer's other frames. Other layers just get a bigger canvas. One undo step. Headless: pass file.

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": "extend_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
topNo
fileNo
leftNo
seedNo
frameNo
layerNo
patchNo
rightNo
bottomNo
sample_xNo
sample_yNo
sample_widthNo
sample_heightNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.3/5.0
Behavior3/5

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

No behavioral annotations exist beyond the title, so the description carries the burden; it does disclose mutation scope well ('One undo step', 'Other layers just get a bigger canvas', 'no new colours appear', frame margins shared across the layer's frames) and the headless file requirement. What it omits is failure behavior: what happens with a zero-size extension, an out-of-bounds sample rectangle, or a sample area smaller than the patch.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then mechanism, then sampling advice, then side effects and the headless note. Roughly a hundred words for a 13-parameter tool with no schema descriptions, and no sentence is 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 mutation tool with zero annotation hints, no schema descriptions, and no output schema, the description covers purpose, mechanism, parameter meanings, side effects, undo granularity, and headless invocation. Only the seed parameter and edge-case failures remain thin, which is minor at this complexity.

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 coverage is 0% across 13 params, so the description must compensate and largely does: directional pixel amounts, layer as 'the active one', sample_* as the source area defaulting to the whole layer, patch size in pixels, frame as the margin source, and file for headless runs. It leaves seed entirely unexplained and never states defaults (patch=6, seed=1) or how sample_x/y relate to sample_width/height.

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?

States a concrete verb+resource ('Grow the canvas by left/right/top/bottom pixels') and the exact mechanism (patch sampling from a sample area that matches neighbouring pixels). The portrait-to-banner analogy plus 'Other layers just get a bigger canvas' pins down scope so the agent can distinguish this from frame/layer creation siblings without opening the schema.

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?

Gives real selection guidance for the tricky input ('Pick a sample of pure background, like open meadow, so the subject isn't copied, and big enough not to repeat') and a stated use case (portrait scene to wide banner), but never names an alternative tool or an explicit when-not-to-use condition.

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