spatial_prepare_screenshot_crop_manifest

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

With no annotations provided, the description carries the full burden and does disclose real side effects: it 'writes one PNG per crop box' and 'updates image-to-model handoffs to real file paths,' and notes it is a 'local tool.' This is genuine behavioral value beyond the schema. But it omits the overwrite/destructive implications (overwrite defaults to true in the schema), and says nothing about failure behavior or prerequisites, leaving a meaningful transparency gap for a file-writing 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 front-loaded with the one-line purpose, followed by a dense behavior paragraph and a concrete example; every sentence carries information. The KB pointer line is slightly cryptic and of marginal invocation value, but it is short. This is lean and well-ordered for a 9-parameter tool.

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 tool is complex (9 params, 0% schema coverage, no annotations) and the description covers its core behavior, inputs, and return payload, with an output schema covering return values. But it lacks stated prerequisites (e.g., that reconstruction_plan_json comes from spatial_plan_screenshot_reconstruction or detected_items_json from spatial_preflight_screenshot_detections), leaves six parameters unexplained, and gives no failure-mode or overwrite guidance. Adequate for invocation but with clear gaps.

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 compensate, and it does for the three invocation-critical parameters: detected_items_json, reference_image, and reconstruction_plan_json are explained through the two input modes, with reconstruction_plan_json shown in the example. However, the remaining six parameters (limit, overwrite, image_size, padding_px, min_crop_px, crop_output_dir) receive no semantic explanation at all, so the compensation is only partial for a 9-parameter tool.

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 opening line states a specific verb and resource: 'Write local prop crops for screenshot-driven Tripo image generation.' The description then details the mechanism (one PNG per crop box, handoff updates, returning a reconstruction JSON payload for the batch planner), which positions it distinctly from pipeline siblings like spatial_prepare_screenshot_decomposition_request, spatial_plan_screenshot_reconstruction, and spatial_prepare_tripo_generation_batch. An agent can tell what this tool does without opening the schema.

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 gives clear invocation context by specifying two valid input modes: 'either detected_items_json plus a local reference image, or a screenshot reconstruction result with crop_tasks,' and it provides a concrete example call with reconstruction_plan_json. However, it never explicitly names alternatives or states when NOT to use this tool versus the spatial_ pipeline siblings, so it stops at clear context without exclusions.

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