Exports Photoshop top-level or selected layers as separate PNGs—trimmed or full canvas—to a folder for cut-outs, parallax assets, and After Effects handoff.
Photoshop: export each top-level layer (or the listed ones) as its own PNG (trimmed or full canvas) into a folder — e.g. cut-outs for After Effects parallax.
| Name | Required | Description | Default |
|---|---|---|---|
| trim | No | ||
| folder | Yes | ||
| layers | No | ||
| document | No | Document name; omit for the active document. |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds real output-shaping context (each layer becomes its own PNG, trimmed or full canvas), which is more than the annotations convey. However, with readOnlyHint=false and destructiveHint=false, the agent still isn't told whether files are written to disk, whether an existing folder is overwritten, whether the source document is modified, or how hidden/empty layers and groups are handled.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One dense sentence front-loads the action and output, then closes with a single clarifying example that earns its place. No redundant restatement of the tool name or of annotation-covered safety traits.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description should say what comes back (file paths, naming convention, what happens when a layer can't be exported) — it says nothing about returns. Coverage of the destructive/overwrite profile is also absent for a tool that writes files, leaving meaningful gaps for a 4-parameter export action.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 25%, with just 'document' described, so the description must carry the rest — and it does substantially: 'trimmed or full canvas' explains the trim boolean, and 'each top-level layer (or the listed ones)' explains the scope of the layers array. The folder parameter's role as destination is implied rather than spelled out, keeping it below a 5.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (export) and resource (each top-level layer / listed layers) with the output format (PNG) and destination (a folder). The example use case ('cut-outs for After Effects parallax') makes it immediately distinguishable from siblings like ps_preview or xapp_photoshopToAE, which move assets into AE rather than rendering per-layer PNGs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description makes clear when it applies: exporting every top-level layer or only a named subset, and gives a representative scenario (parallax assets). It stops short of naming an alternative tool or stating when not to use it (e.g., use ps_saveDocument for a flattened PSD, or a slice/export workflow).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.