Auto-detect the elements (subjects and text) in a design image as relative bounding boxes. Returns: A JSON string with the detected elements (relative bboxes) and their count.
| Name | Required | Description | Default |
|---|---|---|---|
| image | No | The 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?
No annotations are provided, so the description must carry the full burden. It states the return format (JSON string) but does not disclose whether the tool is read-only, idempotent, or has side effects. This is a significant omission for a detection tool.
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 description is extremely concise with two sentences, no wasted words, and directly states purpose and output. It is front-loaded with the action and resource.
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?
The description covers input and output basics but lacks details on coordinate system for relative bboxes, error handling, and assumptions about the input image. Given the tool's simplicity, this is adequate but incomplete.
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 100% for the single parameter 'image', so baseline is 3. The tool description repeats 'design image' but adds no new semantics beyond what the schema already provides (URL or base64 data URL).
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 detects elements (subjects and text) in a design image and returns relative bounding boxes. It distinguishes from siblings 'diagnose' and 'reproduce' by naming a specific detection task, but does not explicitly contrast usage scenarios.
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?
No information is provided about when to use this tool versus alternatives like 'diagnose' or 'reproduce'. There is no guidance on prerequisites, context, 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.