spatial_prepare_screenshot_decomposition_request

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

With no annotations, the description carries the full burden of behavioral disclosure. It does disclose that 'This local planner does not run computer vision' and that it produces a contract and handoffs, which is useful. However, it does not state whether the tool is read-only, whether it has side effects, or what happens to the input files. Some behavioral gaps remain.

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 focused and information-dense, with a clear opening statement, a KB reference, a one-sentence functional summary, and a concrete example. No filler words. The structure is logical and front-loads the core purpose.

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?

While the output schema exists and covers return values, the input parameter semantics are largely missing from the description. An agent would not know what values to provide for style, intent, max_items, room_type, room_origin, room_dimensions, prefer_crop_boxes, room_analysis_json, or include_architectural_fill. The description only scratches the surface with the example and the phrase 'optional room bounds.' This is not enough for reliable invocation.

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 must explain parameters. It only mentions 'reference screenshot, optional room bounds, and optional live room analysis' and shows an example with reference_image and image_size. The remaining nine parameters (style, intent, max_items, room_type, room_origin, room_dimensions, prefer_crop_boxes, room_analysis_json, include_architectural_fill) are left unexplained. This is insufficient for a tool with 11 parameters.

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 opens with a specific verb and resource: 'Prepare a vision-agent request for screenshot decomposition.' It then details what the tool does ('turns a reference screenshot, optional room bounds, and optional live room analysis into a strict detected_items_json contract, vision prompt, and handoffs'), and differentiates it from computer-vision-executing tools by stating 'This local planner does not run computer vision.' The example further clarifies the call signature.

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 clearly positions the tool as the planning/preparation step that feeds into 'Ghost's screenshot preflight, scene graph, crop, Tripo, binding, placement, and validation workflow,' and notes it does not run computer vision. This gives clear contextual guidance for when to invoke it, though it does not explicitly name alternative tools or state when not to use it.

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