Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

render_onion_composite

Render a PNG of a chosen frame with previous frames ghosted red and next frames ghosted blue at a set opacity, so you can view the motion arc in one image without altering the sprite.

Instructions

Write a PNG of frame with up to prev earlier frames ghosted in red and next later frames ghosted in blue (Aseprite's onion-skin convention) at the given ghost opacity — so you can see the motion arc in one image. Does not modify the sprite. 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": {
      "frame": "<frame>",
      "output_path": "<output_path>"
    },
    "name": "render_onion_composite"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
nextNo
prevNo
frameYes
opacityNo
output_pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=false and openWorldHint=true; the description reinforces this with 'Does not modify the sprite' and adds real rendering context (red/blue ghosting convention, opacity applied to ghosts, headless file requirement). It does not disclose failure behavior for out-of-range frames or whether an existing PNG at output_path is overwritten, which keeps it below 5.

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 operation is front-loaded and the two trailing sentences ('Does not modify the sprite', 'Headless: pass file') each add distinct value. The first sentence is long and packs five parameters into one clause, but no sentence is filler.

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, no-output-schema rendering tool with zero schema description coverage, the description covers rendering semantics well but leaves the destination parameter, default behavior, and error cases unexplained. An agent can form a reasonable call, but may guess wrong on output_path and on what happens when prev/next exceed the available frame range.

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

Parameters3/5

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

Schema description coverage is 0%, so the description carries the full burden: it clarifies frame, prev, next, opacity, and gives the file parameter a purpose ('Headless: pass file'). But output_path — one of only two required parameters — is never mentioned in prose (its semantics like overwrite/parent-directory creation are left unstated), and no range or boundary behavior is given for prev/next or opacity.

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?

Names a specific verb and artifact ('Write a PNG of frame') and explains precisely what is composited: prev frames ghosted in red, next frames in blue, Aseprite convention, at a given opacity. An agent can tell this is a rendering/export tool, not a settings tool like set_onion_skin. It stops short of explicitly naming the sibling it contrasts with, which is why it is a 4 rather than 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 Guidelines3/5

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

Usage is implied by the rationale 'so you can *see* the motion arc in one image', and 'Headless: pass file' gives a concrete call condition. However, there is no explicit when-not, no mention of which sibling to use for merely reading or changing onion-skin settings, and no guidance on what to do if no frames exist in the requested range.

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