Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

save_sprite

Saves the active sprite to disk, using the given path for save-as or its existing filename, and persists edits. In headless mode, pass both file and path to write a copy without changing the source.

Instructions

Save the active sprite to disk: to path if given (save-as; the document's filename follows it), else to its own filename — errors if the sprite is untitled and no path is given. Live: persists the edits sitting in the open editor. Headless: mutating tools already save to file on their own; use this with both arguments to write a copy of file under a new path (the source file on disk stays untouched).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "save_sprite"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
pathNo

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?

Annotations only carry openWorldHint, so the description carries most of the behavioral load and does so well: it explains live-mode persistence of pending editor edits, the untitled-sprite error, and that in headless mode the source file on disk stays untouched. Missing only whether an existing target path is overwritten or whether the tool returns the written path.

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, then the two mode branches in sequence; every clause carries information. The parenthetical asides and heavy backtick use add slight density but no wasted 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 two-parameter mutation with no output schema and thin annotations, the description covers both execution modes, the error case, and the disk side effects. Only the return value and overwrite semantics are left implicit.

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 define both parameters, and it does: path is the save-as destination that also renames the document, file is the headless-mode source. What remains unstated is how file behaves in live mode (the schema default is null and it appears ignored there).

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 ("Save the active sprite to disk") and scopes it to the single active sprite, which implicitly separates it from broader siblings like save_all_sprites. The save vs save-as distinction is stated in the first clause.

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?

Explicitly branches on the path argument (save-as with document rename vs overwrite-in-place), states the failure condition (untitled sprite with no path), and gives an explicit when-to-use rule for headless mode. An agent can pick the correct call form without inference.

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