Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

paint_mountains

Paint layered mountain ranges above a horizon in Aseprite with configurable time-of-day lighting, snow, trees, and sun placement for scene backgrounds.

Instructions

Paint mountain ranges standing on row horizon: up to three ranges, the far one palest and hazy at its foot, the near one dark. time is dawn, day, sunset, or night, matching paint_sky. The tallest peak reaches size (0-1) of the way up from the horizon. With sun at [x, y], faces toward it are lit and the ranges dip there so it shows between them; without it the light comes from the right. snow caps the far range and trees puts a treeline on the nearest. seed changes the shapes. They go on a new layer named layer just above the layer named above (the sky), or at the bottom if there is none. Follow with reflect_in_water. 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": "paint_mountains"
  }
}

Input Schema

NameRequiredDescriptionDefault
sunNo
fileNo
seedNo
sizeNo
snowNo
timeNosunset
aboveNoSky
layerNoMountains
treesNo
rangesNo
horizonYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations carry only a title, so the description must do the behavioral work and largely does: it declares that output goes on a new layer named ``layer`` placed just above ``above`` (or at the bottom when absent) and that the whole operation is one undo step. That layer/undo/headless disclosure is genuinely useful context an agent could not get from structured fields.

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?

Dense but front-loaded: the core action and anchor come first, then lighting, then optional decorations, then layer placement and follow-up. Every clause conveys a distinct behavior; there is no filler despite the length being driven by 11 parameters.

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 an 11-parameter, no-output-schema drawing tool with only a title annotation, the description supplies the parameter semantics, placement rules, undo cost, and the recommended next tool. Nothing an agent needs in order to invoke it correctly appears to be missing.

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% across 11 parameters, so the description has to carry all semantics, and it does: ``ranges`` capped at three with a depth/haze ordering, ``time``'s four allowed values, ``size`` as a 0-1 fraction of peak height, ``sun`` as [x, y] with directional lighting effects, plus ``snow``, ``trees``, ``seed``, ``layer``, ``above``, and ``file``. Each parameter's effect on the picture is explained rather than restated.

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 and resource ('Paint mountain ranges') plus the anchoring input (row ``horizon``), so an agent knows exactly what will be produced. It also implicitly distinguishes itself from ``paint_sky`` by requiring a horizon row and referencing the sky layer as the insertion point.

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 workflow guidance: ``time`` must match ``paint_sky``, and the tool should be followed by ``reflect_in_water``; also names the headless escape hatch via ``file``. What is missing is any exclusion or error guidance, e.g., what happens if ``horizon`` is out of range or the named layer does not exist.

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