Removes unwanted objects from a Photoshop selection or rectangle by applying content-aware fill to the active or named layer.
Photoshop: content-aware fill the current selection (or rect [x,y,w,h]) on the active/named layer — removes objects.
| Name | Required | Description | Default |
|---|---|---|---|
| rect | No | ||
| layer | No | Layer name (searched in groups too); omit for the active layer. | |
| expand | 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?
Annotations already declare it is a mutation (readOnlyHint=false) with no open-world access. The description adds useful effect context ('removes objects') but omits whether a selection is mandatory, what happens if none exists, whether pixels are replaced on the current layer or a new one is produced, and whether the change is undoable. There is also a mild tension between 'removes objects' and destructiveHint=false, though the annotation plausibly refers to not deleting layers/documents rather than pixel overwrite.
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?
A single dense sentence with the operation front-loaded, followed by the target and outcome. No filler; the only mild cost is heavy shorthand ('rect [x,y,w,h]') that compresses rather than explains.
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 4-parameter mutation with no output schema, the description covers what the tool does and one parameter's format, but leaves the selection precondition, the meaning of 'expand', and the result/undo behaviour unstated. Adequate to attempt a call, not adequate to call it confidently in edge cases.
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 50%: layer and document are documented in the schema, while rect and expand are not. The description partly compensates by giving rect's format ([x,y,w,h]) and its role as the alternative to an existing selection, but 'expand' is left entirely undefined in both schema and description, so the parameter surface is not fully explained.
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 ('content-aware fill') plus the exact target (current selection or rect on the active/named layer) and the user-facing outcome ('removes objects'). This is enough for an agent to distinguish it from neighbours like ps_removeBackground, ps_selection, or ps_applyFilter without opening any schema.
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 goal ('removes objects') implies the scenario, but there is no explicit when-to-use/when-not, no mention of prerequisites such as an existing active selection, and no pointer to an alternative (e.g. ps_selection to build the selection first, or ps_removeBackground for subject cutouts). Usage must be inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.