Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

select_layer

Idempotent

Makes a layer active so subsequent edits apply to it, accepting a Group/Layer path. Use it as a step in headless edit batches, where active-layer state is not retained between calls.

Instructions

Make a layer active, so the next edits land on it. name may be a "Group/Layer" path. Headless forgets this between calls, so use it as a step in edit_batch there.

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": {
      "name": "<name>"
    },
    "name": "select_layer"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
nameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only supply idempotentHint=true, so the description carries the real behavioral load and does add value: it discloses that in headless mode the active-layer state is forgotten between calls, which materially changes how an agent must sequence calls. It also reveals that name can be a composite "Group/Layer" path. It does not say what happens if the layer does not exist or what the call returns.

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?

Three short clauses, benefit-first, with the most consequential caveat (headless state loss) placed before the actionable guidance. Minor noise from RST double-backtick markup and the slightly vague "there," but no filler sentences.

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 simple two-parameter, non-annotated (beyond idempotency), output-schema-less tool, this covers the essential effect, the path syntax, and the headless persistence caveat. The only real hole is the undocumented file parameter and unstated behavior when the named layer is absent.

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 description coverage is 0% across two parameters, so the description must compensate and only partly does: it explains that name accepts a "Group/Layer" path, which the string schema does not convey. The second parameter, file, is never mentioned, leaving its role (target document?) undocumented in both schema and description.

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?

States a specific verb and resource plus its effect: "Make a layer active, so the next edits land on it." That distinguishes it from the layer-management siblings (add_layer, rename_layer) and from the select_* family by targeting a named layer. It stops short of explicitly contrasting with select_all or select_by_color, so a 4 rather than a 5.

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 concrete when-to-use condition (before edits that should land on that layer) and a specific headless pattern: call it as a step within edit_batch because selection is not persisted between calls. No explicit when-not-to-use or named alternative tool, which keeps it out of 5 territory.

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