Run a named Photoshop operation with arguments and return its result as JSON instead of writing ExtendScript.
Run one Photoshop operation by name (see ps_catalog), e.g. {"operation":"create_text_layer","args":{"text":"Hi"}}. Returns the operation result JSON. Prefer this over writing ExtendScript.
| Name | Required | Description | Default |
|---|---|---|---|
| args | No | operation parameters | |
| operation | Yes | operation name from ps_catalog (without the photoshop_ prefix) |
Changes observed during successful MCP inspections.
v1.1.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full behavioral burden. It only says it returns the operation result JSON; it does not disclose that the dispatched operations can be destructive to the open document, whether errors are surfaced per operation, or that args must match the catalog signature. For a generic execution surface this is thin.
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?
Three short sentences: purpose plus example, return value, and the ExtendScript alternative, with the primary action front-loaded. No filler; the example earns its place by disambiguating the nested args.
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?
For a two-parameter dispatcher with a free-form args object and no output schema, the description supplies the name source, a call example, and the return type. The remaining gap is per-operation argument discovery and failure behavior, which it only partially offloads to ps_catalog.
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 100%, so the baseline is 3, but the description exceeds that by giving a concrete call example that shows the nested args shape and its free-form object nature, which the schema leaves as additionalProperties. It still doesn't say where per-operation arg schemas live beyond the catalog reference.
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 and resource: 'Run one Photoshop operation by name', and names the catalog that supplies valid names. It is distinguishable from ps_catalog (which lists) and ps_execute_script (which it says to avoid). It does not, however, distinguish itself from the many typed photoshop_* operation tools that overlap with it.
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?
Gives a clear directive to look up names in ps_catalog and an explicit preference against writing ExtendScript, which is a real alternative-avoidance statement. It omits when to prefer ps_do over the equivalent typed tools such as photoshop_create_text_layer, and any when-not-to-use conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.