gradient_fill

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

With no annotations, the description does disclose that it mutates a layer/selection, that x2/y2 null resolves to the bottom-right of the image, that layer_name defaults to the active layer, and that it returns a status dict. It doesn't say whether existing pixels are replaced, whether the operation is undoable, or how blend/alpha is 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?

A single summary sentence followed by a scannable bullet list of parameters; front-loaded and easy to parse. Some redundancy with schema defaults, but that redundancy is what supplies the missing semantics here.

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 9-parameter, zero-annotation, no-output-schema tool, the description covers purpose, every parameter, defaults, and return type. The remaining gap is failure/permission behavior and the destructive nature of the fill.

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%, so the description carries the full burden and does it well: all nine parameters get a one-line meaning plus defaults, and it explains the non-obvious null-to-bottom-right behavior of x2/y2 that the schema leaves opaque.

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?

The first line names a specific verb and resource ('Fill a layer or selection with a gradient'), which is enough for an agent to tell it apart from adjacent drawing tools. It stops short of explicitly differentiating from siblings like fill_layer, fill_selection, or apply_vignette.

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?

Mentioning 'layer or selection' implies targeting behavior, but there is no explicit guidance on when to choose this over fill_layer or fill_selection, nor any stated prerequisites such as an open image or active selection.

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