Add controllable grain or noise to a GIMP layer by setting intensity from 0.0 to 1.0, targeting a named layer or the active one, to simulate film grain or texture.
Add noise/grain to a layer.
Parameters:
amount: Noise intensity 0.0-1.0 (default 0.2)
layer_name: Target layer; defaults to active layer
image_index: Target image index (default 0)
Returns status dict.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | No | ||
| layer_name | No | ||
| image_index | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full behavioral burden, yet it only says "Returns status dict." It does not say the layer is modified destructively in place, whether the operation is undoable, whether a prior selection is respected, or what happens if layer_name does not resolve — all material for a mutation tool with zero annotation coverage.
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?
The effect sentence is front-loaded and the parameter list is easy to scan. The default values restated in the parameter list duplicate the schema, which is mild redundancy rather than confusion.
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?
Parameters are fully covered, but for a destructive image-editing mutation with no annotations and no output schema, the definition should still disclose undo/edit-state implications and failure behavior. What is present is adequate; what is absent is the risky part.
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 description coverage is 0%, and the description compensates well: it documents all three parameters, including the 0.0–1.0 range for amount and the active-layer fallback for layer_name. It loses a point because it does not explain how layer_name is matched (exact name vs. index vs. partial) or what an out-of-range amount does.
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?
"Add noise/grain to a layer" states a specific verb and resource plus the visual effect, which is enough to separate it from siblings like blur, denoise, or sharpen. It stops short of naming any sibling or clarifying the boundary with the other stylize filters (e.g. apply_pixelate, apply_emboss).
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 never says when to reach for this tool versus apply_gaussian_blur, apply_pixelate, or the generic gegl_apply_filter. The only guidance is a metaparameter default ("defaults to active layer"), which is about targeting, not about tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.