Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

animate_parts

Create cut-out puppet animations by setting part poses across frames; interpolate motion with pivots, parent links, easing, and looping for Aseprite sprites.

Instructions

Animate a character made of part layers like a cut-out puppet. poses are key poses: {"frame": 1, "part": "Arm", "angle": -20, "x": 0, "y": 1}, with angle in degrees clockwise and x/y a move in pixels; any left out are 0. Frames between keys are filled in (easing is smooth or linear), and with loop the last pose eases back to the first. pivots maps a part to the [x, y] it turns about (a shoulder, a hip; its middle by default). parents maps a part to the one it hangs from, so {"Forearm": "Arm"} keeps the forearm on the arm. Each part is drawn from its from_frame pixels, turned with RotSprite-style rotation so edges stay crisp. Frames are added as needed and tagged tag. Check the result with look_animation and check_loop. 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": {
      "poses": "<poses>",
      "frames": "<frames>"
    },
    "name": "animate_parts"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNomove
fileNo
loopNo
posesYes
easingNosmooth
framesYes
pivotsNo
parentsNo
from_frameNo
duration_msNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.8/5.0
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 does so well: it discloses interpolation between keys, easing options, loop-back behavior, default pivot at the part's middle, inheritance via parents, RotSprite rotation, that frames are added and tagged automatically, and that the whole call is 'One undo step'. The main omission is what the call returns, which matters since there is no output schema.

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?

Information is front-loaded — the core mechanic first, then per-parameter details, then verification and environment notes. The inline example and parenthetical asides ('a shoulder, a hip', 'its middle by default') earn their space, though the prose is dense enough that a short bulleted parameter list would scan faster.

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 a 10-parameter mutation tool with no annotations and no output schema, the description is substantially complete: mechanics, defaults, side effects, and verification path are all present. The gaps are the undocumented required 'frames' parameter, 'duration_ms', and the return value, which an agent would have to discover by calling.

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?

With 0% schema description coverage the description must carry parameter meaning, and it explains poses (with a concrete example), angle direction in degrees clockwise, x/y in pixels, omitted values defaulting to 0, easing values, loop behavior, pivots, parents, from_frame, tag, and file. Two parameters are left undefined, notably the required 'frames' and 'duration_ms', which is the reason it stops short of full marks.

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?

The opening sentence gives a specific verb and resource ('Animate a character made of part layers like a cut-out puppet'), which is precise enough to separate this from generic motion tools like ambient_motion or apply_timing. It does not explicitly contrast with a sibling animator, but the 'part layers' framing makes the target scenario unambiguous.

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?

It closes with 'Check the result with look_animation and check_loop', which gives useful follow-up workflow but not selection guidance. There is no statement of when to prefer this over other animation-related siblings, nor any exclusions or prerequisites beyond the headless 'file' note.

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