spatial_plan_composition_iteration

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It explicitly states this is a local planner that 'does not mutate the Unreal Editor scene' and that it returns review candidates and revalidation steps rather than applying changes. This is meaningful transparency for a tool in a mutation-heavy toolset, though it could go further on how outputs are meant to be consumed.

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 compact, front-loaded with the core purpose, and adds only useful context: KB reference, a clear behavioral statement, and a short invocation example. There is no filler or redundant restating of schema fields.

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 gives enough pipeline context to understand where this tool fits and confirms it is a non-mutating dry-run planner. The output schema covers return values, so those do not need to be spelled out. However, given 8 undocumented optional parameters and no explicit differentiation from sibling spatial planning tools, the description is not fully complete for confident parameter tuning and tool selection.

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?

Input schema description coverage is 0%, so the description must compensate, but it only meaningfully clarifies composition_plan_json and validation_result_json. Parameters such as max_iterations, nudge_distance, clearance_padding, surface_tolerance, reference_image, and screenshot_notes are left unexplained. The example only shows validation_result_json, leaving the semantics of the other seven parameters largely under-specified.

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 names a specific function: plan dry-run corrections from placement validation and viewport notes. It identifies the consumed inputs (composition plan + validation result), the produced outputs (transform candidates, surface-probe handoffs, revalidation, screenshot evidence), and the non-mutating nature. This is specific enough to distinguish it from sibling tools like spatial_validate_placement or spatial_apply_composition_plan.

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 context about when this tool fits: after placement validation and before applying changes, acting as a dry-run local planner. It also explicitly states it does not mutate the scene, which implies it is for planning rather than applying. However, it does not explicitly name sibling alternatives or give when-not-to-use conditions.

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