draw_box

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

With annotations already declaring readOnlyHint=false, openWorldHint=false and destructiveHint=false, the description adds real behavioral context beyond them: the exclusive `end` boundary, that 'add' replaces voxels present in the region and grows the part, and that 'carve' removes the part's voxels. Note the mild tension between 'carve removes voxels'/'add replaces voxels' and destructiveHint=false, though the existence of a sibling `undo` tool makes the non-destructive hint defensible.

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?

Front-loads the core semantics (verb, resource, half-open interval) in the first sentence, then spends the remaining lines on one dense worked example plus a single carve use-case line. The example is longer than a bare definition but it earns its place; no filler sentences about the tool's importance.

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 6-parameter mutation tool with no output schema, the description plus the 100%-covered schema covers coordinates, bounds, modes and color requirements well enough to invoke correctly. It does not address return values or whether coordinates outside the part's current extent are permitted, which is a minor gap given the tool's complexity and the presence of `preview`/`inspect` siblings for verification.

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 100%, so the baseline is 3; the description earns an extra point by supplying a worked example that translates physical model units into integer voxel coordinates ('a body 1.6 m wide ... start [-8, 3, -20], end [8, 9, 20] (16 x 6 x 40 voxels)'), which clarifies the model frame and scale that the schema alone does not pin down.

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 family (add/paint/carve) and resource (rectangular block of cells / voxel box), and the half-open interval notation makes the geometric primitive unambiguous. This clearly distinguishes it from siblings draw_cylinder, draw_ellipsoid and draw_wedge without needing to open their schemas.

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?

Gives concrete usage context ('Carve a cabin interior or wheel arches with mode `carve`') and a fully worked example with realistic dimensions, which tells the agent the intended scale and coordinate convention. It does not, however, explicitly state when to prefer a box over the other draw_* primitives or any prerequisites (e.g. the part must already exist), so it is clear but not exhaustive.

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