spatial_plan_screenshot_reconstruction

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

With no annotations, the description carries the behavioral burden and largely meets it: it discloses that this is a local planner (not CV), that it returns the detected_items_json schema when detections are absent, that matching can produce a 'guarded Tripo image/text handoff', and that scene-graph relations are folded into placement hints. It stops short of describing side effects or external generation implications, but 'dry-run' signals non-mutating planning.

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?

Four short paragraphs front-load the core purpose, add a KB pointer, then cover conditional behavior and close with a concrete example. No filler, though the internal jargon ('Tripo crop handoffs', 'guarded ... handoff') is dense.

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 tool with 18 parameters and zero annotations, the description communicates the orchestration role but leaves important operational details unspecified: parameter semantics, prerequisites, output expectations, and the relationship to the spatial_prepare_*/spatial_infer_* siblings. The example only demonstrates a single-argument call.

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%, and the description compensates only minimally: reference_image appears in the example, and detected_items_json/scene_graph_json are implied by the conditional behavior. The other 15 parameters (limit, room_dimensions, existing_asset_paths, include_text_fallbacks, generate_missing_with_tripo, etc.) get no semantic explanation.

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 sentence names a specific action ('Plan ... reconstruction'), scopes it to screenshots, and mentions Tripo crop handoffs. The body reinforces the boundary ('does not perform computer vision by itself'), which separates it from vision-stage siblings, though it never names those siblings explicitly.

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 conditional context: no detections → return schema; detections → map props and run dry-run placement; scene graph → fold support/wall-anchor relations. It does not state when to prefer this tool over sibling planners or vision/asset-prep tools, so usage guidance is implicit rather than explicit.

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