Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

edit_batch

Run multiple Aseprite editing steps as one undoable batch; if any step fails, none apply.

Instructions

Run several editing tools as one undo step, so one Ctrl-Z reverts them all. Each step is {"tool": "draw_line", "args": {...}}, in order. If any step fails, none of them apply. The pixel cap covers the whole batch. Steps can't see each other's results, and tools that save or export can't be batched. 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_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
labelNoAI edits
stepsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations supply only a title, so the description carries the full behavioral burden and does so well: all-or-nothing semantics ('if any step fails, none of them apply'), undo grouping, a shared pixel cap across the batch, and the constraint that steps cannot read each other's results. These are exactly the non-obvious traits an agent needs before composing a batch.

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?

Five short sentences, front-loaded with the core purpose, then constraints in descending order of importance. Every sentence adds information that is not available in the schema or annotations; nothing is 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?

For an atomic multi-step mutation tool with no output schema, the description covers composition format, failure semantics, and key restrictions. The remaining gap is what a caller sees on failure (which step errored, whether partial state is reported), which matters for recovery from an all-or-nothing operation.

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 description coverage is 0%, so the description must compensate, and it explains the most important parameter in detail: the shape of each step ('{"tool": "draw_line", "args": {...}}') and that order is preserved. It also clarifies that file belongs at the top level in headless mode. The label parameter is never mentioned, leaving one of three parameters undocumented.

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 ('Run several editing tools as one undo step') plus the outcome ('one Ctrl-Z reverts them all'), which is a distinct capability from single-purpose siblings like draw_line or batch_apply_palette. An agent can tell immediately that this is a meta-tool for composing other edits.

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 when-to-use context (grouping edits into one undo unit) and an explicit exclusion ('tools that save or export can't be batched'), plus a routing hint for headless mode ('pass file here, not in the steps'). It does not explicitly contrast against invoking the individual tools sequentially, but the atomicity framing implies that choice.

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