Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

edit_in_selection

Restrict Aseprite edits to the current selection, applying all steps as one undo and reverting any changes made outside the selected area.

Instructions

"Fix this bit": run editing tools so they change only what's inside the current selection, as one undo step. Anything they'd do outside it, on any layer or frame, is put back. Steps are written as in edit_batch. Select the area in Aseprite first; look with selection shows what's selected. Steps can't change the frames, layers, or canvas size. Headless: pass file here, not in the steps.

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": {
      "steps": "<steps>"
    },
    "name": "edit_in_selection"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
labelNoAI edits in selection
stepsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.3/5.0
Behavior5/5

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

With only a title annotation, the description carries the full burden and does so well: it discloses atomicity (single undo step), the reversion guarantee for any effects landing outside the selection on any layer or frame, hard constraints on what steps may alter, and the headless file-passing convention. These are exactly the behavioral traits an agent could not infer 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense and front-loaded: the core guarantee and its verification method come before the constraints and headless note. The quoted 'Fix this bit' opener and doubled-backtick artifacts are minor noise, but no sentence is redundant.

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 mutation tool with free-form nested step objects, no annotations, and no output schema, the description covers the essential contract: prerequisites, atomicity, scope reversion, and parameter routing. The remaining gap is the undefined shape of individual steps, which it defers to ``edit_batch`` rather than explaining.

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 coverage is 0%, so the description must compensate. It clarifies ``file`` (pass here rather than inside steps when headless) and points at ``edit_batch`` for the shape of ``steps``, which is real added meaning, but the ``steps`` element structure is entirely undefined and ``label`` is never mentioned.

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 — run editing tools constrained to the current selection as one undo step — and immediately contrasts that with the unconstrained behavior of the underlying tools. It names the related siblings (``edit_batch`` for step format, ``look`` for inspecting the selection), so an agent can place it relative to alternatives without opening a schema.

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 a clear prerequisite (select the area in Aseprite first) and a concrete way to verify readiness (``look`` with ``selection``). It also states the limitation that steps cannot change frames, layers, or canvas size. It stops short of saying what to do instead when those changes are needed, so it is strong context rather than explicit routing.

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