Aseprite AI Artist

Overview Schema Source Related Servers Discussions Admin

Manage sprites

sprite_manage

Destructive

Manage open Aseprite sprites: create, open, focus, resize, save, close, and define slices for engine hotspots or 9-patch regions.

Instructions

Open, create, focus, resize, save and close sprites in the running Aseprite session. Ops: 'list' (open documents), 'new', 'open', 'activate', 'save', 'save_as', 'close', 'resize_canvas', 'set_properties', 'slice_create', 'slice_update', 'slice_delete'. Canvas resize keeps existing pixels — pass an anchor to say where they land. Slices name a rectangular region of the canvas for an engine to read back — a 9-patch panel's center, or a hotspot's pivot.

Input Schema

Name	Required	Description	Default
`op`	Yes
`name`	No	Slice name. Required for 'slice_create'; identifies it for update/delete.
`path`	No	File path for 'open' and 'save_as'.
`color`	No	For slice ops: slice colour in the timeline, #rrggbb.
`force`	No	Allow 'close' to discard unsaved changes. Ask the user before setting this.
`pivot`	No	For slice ops.
`width`	No
`anchor`	No	Where existing pixels sit after 'resize_canvas'.	center
`bounds`	No	Slice rectangle. Required for 'slice_create'.
`center`	No	For slice ops: nine-slice centre region, relative to `bounds`.
`height`	No
`sprite`	No	Which sprite: its id as '#7' (what every result reports back, and the only unambiguous form — two unsaved documents are both called 'Sprite'), its filename, or its display name. Omit to use the sprite Aseprite has focused.
`colorMode`	No	For 'new'. Indexed keeps a sprite honest about its palette.
`pixelAspect`	No	e.g. '1:1' or '1:2'.

Output Schema

Name	Required	Description
`id`	No	Stable id of the affected document; pass it back as '#<id>'.
`op`	Yes
`name`	No	Slice name, for 'slice_delete'.
`path`	No
`slice`	No	The affected slice, for 'slice_create'/'slice_update'.
`width`	No
`height`	No
`sprite`	No
`sprites`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.8.2Nov 7, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is carried by structured data. The description adds useful operational context beyond that ('Canvas resize keeps existing pixels', what slices are for), but it never says which ops are the destructive ones (close/save), nor that ops act on a session-bound focused sprite. Solid addition, not rich.

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 dense sentences, front-loaded with the verb/resource scope before the op list and the two clarifying notes. Every sentence contributes (op inventory, resize behaviour, slice semantics); no filler, though the op list is long by necessity.

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 14-parameter, 12-op multiplexed tool with nested objects and an output schema, the description gives an adequate map: full op inventory plus targeted clarifications for the two least obvious families (resize anchor, slices). It stops short of per-op parameter pairing, but the schema's per-field op hints largely cover that.

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 coverage is a high 79%, so the baseline is 3, and the description genuinely adds meaning beyond it: the anchor parameter's effect on where existing pixels land, and the purpose of slice fields (nine-slice 'center', hotspot 'pivot'). It clarifies semantics of ops-scoped parameters rather than just restating names.

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?

Opens with a specific verb list and resource ('Open, create, focus, resize, save and close sprites in the running Aseprite session') and enumerates all 12 supported ops, so the agent knows the exact capability surface. It does not, however, name or differentiate itself from close siblings like sprite_info, transform, or look, leaving that routing to inference.

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?

Usage is only implied through the op enumeration and one conditional note ('Omit to use the sprite Aseprite has focused'). There is no explicit when-to-use-this-vs-alternative guidance, e.g. why resize_canvas here rather than transform, or when to prefer sprite_info over 'list'. A capable agent can infer intent from op names, but nothing routes it deliberately.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server