Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

inbetween

Generates intermediate frames between two pixel-art key poses by dithering pixels between them, giving a first-pass guide for shape-changing motion to draw over.

Instructions

Fill in count frames between the key pose on from_frame and the one on the next frame, then return a picture of the result. Unlike tween_frames it handles a pose that changes shape: both poses slide toward each other and trade pixels through an ordered dither, so no new colors appear. smear makes the middle frame hold both poses at once, for fast moves. Other layers hold still. It's a first pass to draw over, not finished art. easing: linear, ease_in, ease_out, or smoothstep. 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": {
      "from_frame": "<from_frame>"
    },
    "name": "inbetween"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
countNo
layerNo
smearNo
easingNosmoothstep
max_sizeNo
from_frameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.5/5.0
Behavior4/5

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

Only a title annotation is supplied, so the description carries the full load, and it does real work: "One undo step" quantifies reversibility, "Other layers hold still" bounds the blast radius, "no new colors appear" discloses the dither constraint on output, and "Headless: pass `file`" reveals an out-of-app execution mode. It stops short of stating what happens to frame count/indices downstream or whether the source key poses are modified, which would matter for a mutating tool with no safety annotations.

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 and scope, then follow-on behavior, then option notes — a sensible order, and each sentence carries information. It is somewhat dense with backticked jargon and could split the easing/headless details more cleanly, but there is no filler.

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?

With 7 parameters, no annotations beyond a title, and no output schema, the description covers the operation, its sibling differentiation, side effects, and most parameter meanings. The remaining holes — `max_size` and precise `layer` targeting semantics — are the only reasons it falls short of complete.

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%, so the description must compensate, and it explains `count`, `from_frame`, `smear`, `file`, and — most valuably — enumerates `easing` values (linear, ease_in, ease_out, smoothstep) that the schema leaves as a bare string, plus the fact that the default is smoothstep implicitly. It leaves `max_size` entirely unexplained and `layer` only obliquely covered by "Other layers hold still."

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?

"Fill in `count` frames between the key pose on `from_frame` and the one on the next frame" states a specific verb, resource, and source/target anchors, and the return value is named ("return a picture of the result"). It explicitly separates itself from `tween_frames` by noting it handles a pose that changes shape, so an agent can disambiguate without opening either schema.

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

Usage Guidelines5/5

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

It names the alternative (`tween_frames`) and the condition that selects this one: poses that change shape rather than interpolate cleanly. It further scopes usage with "`smear` ... for fast moves" and the caveat "a first pass to draw over, not finished art," which tells the agent when this is a rough blocking step versus a final render.

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