preview_hull

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

No annotations provided, so the description carries full burden. It discloses the merge/precedence order of inputs (spec_path read before spec and patch; spec merged over preset), which is useful behavioral context. However, it doesn't state cost, latency, whether the build persists, or error behavior for an operation that constructs geometry.

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?

Opens with the outcome (preview image + stats), then itemizes inputs tersely. The wrapped JSON-Patch example is well-placed. Slightly dense with formatting quirks (pedantic code-span spacing) but every line earns its place.

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 5-param, no-annotation, no-output-schema tool, the description covers the input model thoroughly including precedence ordering. Gaps remain: no output schema means the 'stats' return is uncharacterized, and the spec structure is outsourced to hull_design_guide without saying what's in it.

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: each parameter gets a meaning, the merge/precedence rules are explained, and the patch param includes a concrete example. Loses a point because list-item-by-name behavior is mentioned only in passing and spec format is deferred to an external guide.

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?

States a specific verb+resource ('Build a hull and return a preview image') and enumerates exactly what the preview contains (3/4 above/below, front, side, top) plus stats. This distinguishes it from sibling preview_interior and preview_game_vehicle, though it doesn't name them 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 lists five input sources (spec, preset, design, patch, spec_path) implying these are alternative starting points, but never states when to pick one over another or that they're mutually exclusive/merged. No exclusions or alternative tools named.

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