Un-flatten a flat design image into editable layers and reproduce it bit-perfect, returning the fidelity score. Returns: A JSON string with a bit_perfect flag and fidelity metrics (mae, psnr, exact-match %, stray px).
| Name | Required | Description | Default |
|---|---|---|---|
| image | No | The source design image as an http(s) URL or a base64 data URL. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It explains the process and output, including fidelity metrics, but does not disclose potential side effects (e.g., whether the image is saved or if the operation is destructive). It is adequate but not fully transparent.
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?
Two sentences: first sentence concisely states the action and second sentence describes the return value. No unnecessary words, highly efficient.
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?
Given the complex operation (un-flattening and reproducing bit-perfect), the description is fairly complete by specifying the output format. However, it could benefit from mentioning supported image formats or constraints on the input image. No output schema exists, so the description compensates well.
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?
The input schema covers 100% of the parameter 'image' with a clear description. The tool description repeats the return format but adds no additional meaning to the parameter beyond what the schema already provides, so baseline 3 is appropriate.
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 description clearly states the tool's action: un-flatting a flat design image into editable layers and reproducing it bit-perfect, specifically returning a fidelity score. This distinctly differentiates it from sibling tools 'autodetect' and 'diagnose'.
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 implies the tool is for converting flat images into editable layers, but it does not explicitly state when to use it over 'autodetect' or 'diagnose', nor does it provide any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The three tools have distinct primary purposes: detection, scoring, and reproduction. However, reproduce also returns fidelity metrics which overlap with diagnose, potentially confusing an agent on which to use for scoring.
All tool names are single lowercase verbs (autodetect, diagnose, reproduce), following a consistent and predictable pattern.
With only 3 tools, the server is under-scoped for general design image processing, lacking basic operations like loading or editing images. However, for a focused pipeline, it might be acceptable.
The tool surface lacks fundamental operations such as image input/output or layer manipulation, creating significant gaps that would cause agent failures in most workflows.