Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

reflect_in_water

Fills the area below a horizon line with water that mirrors the artwork above it, adding ripples, tint, depth, and a sun path. Creates the reflection on a new layer in one undo step.

Instructions

Fill everything below row horizon with water that mirrors what is above it. The reflection ripples more the nearer it comes (ripple, 0 for a still mirror) and sinks into tint with depth (0-1). With more than one frame the ripples move as a seamless loop over all of them, and anything animated above is reflected frame by frame. sun_x lays a broken path of light down the water under the sun. layers are the top-level layers to reflect (the sky, hills, a castle); the water goes just above them, so a foreground kept on higher layers stays in front and out of the reflection. By default everything visible is reflected and the water goes on top. It is a new layer named layer. One undo step. 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": {
      "horizon": "<horizon>"
    },
    "name": "reflect_in_water"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
tintNo#0c1030
depthNo
layerNoWater
sun_xNo
layersNo
rippleNo
horizonYes

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 only a title, so the description bears the full burden, and it delivers: it discloses that the tool creates a new layer named `layer`, that it costs one undo step, how multi-frame ripple looping works, and that animated content is reflected frame by frame. Minor gaps remain around failure conditions and whether anything existing is ever modified.

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 core action, then parameter behavior, then defaults and the new-layer/undo contract. Dense but every sentence carries information; the backtick-heavy inline parameter naming makes it slightly harder to scan than a tighter structure would.

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?

For an 8-parameter compositing tool with no output schema and only a title annotation, the description covers inputs, side effects, undo cost, and headless mode. It does not indicate what the call returns (e.g. the new layer's identifier), which is the one loose end.

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 coverage is 0%, yet the description gives meaning to all eight parameters: `horizon` as the waterline row, `ripple` (0 = still mirror), `tint` and `depth` (0-1), `sun_x` as a light path, `layers` as the sources to reflect, `layer` as the output name, and `file` for headless use. This fully compensates for the undocumented schema.

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 specific verb and resource in the first clause: filling everything below row `horizon` with a mirrored water reflection. It goes further to name the resulting artifact (a new layer called `layer`), which makes the effect unambiguous and distinguishable from other layer-creation tools.

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 clear context: defaults reflect everything visible with water on top, and `layers` is the lever for keeping a foreground out of the reflection. It also notes the headless `file` path. What is missing is any explicit exclusion or pointer to a sibling alternative for cases this tool doesn't fit.

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