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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description reinforces this by explaining the operation is stateless and leaves saved cloud projects untouched, which is valuable because 'appending commands' could otherwise read as a mutation. It also discloses hard constraints (integer coordinates 0..63, colors as #RRGGBB or palette index) that annotations do not cover, though it says nothing about error behavior or whether command order matters.

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 purpose, statelessness, and the key 'don't emit raw voxel JSON' advice before the grammar reference, which is dense but each command entry carries unique syntax the agent cannot infer. It is long, but the length is justified by the opaque command DSL; little is wasted.

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?

There is no output schema, and the description covers the return conceptually ('compute a new model handle'), the full command grammar, and the coordinate/color conventions. It omits a few details an agent might want, such as whether commands apply sequentially, how errors in a command list are reported, or whether the returned handle feeds into other tools.

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 only 33% (only 'model' is documented), so the description must compensate and largely does: it fully specifies the command tuple grammar for all twelve command types, coordinate range, and color encoding. The 'palette' parameter is never named explicitly, though the 'zero-based palette index' color rule implies its role, leaving a small gap.

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 ('compute a new model handle'), resource (VoxelDraft model handle), and mechanism ('appending compact modeling commands'). The explicit note that it is stateless and does not modify a saved cloud project distinguishes it from siblings like save_voxel_model and create_voxel_model without opening 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 a clear directive to use the compact instruction stream rather than one JSON object per voxel, plus selection guidance among command types (box/roof/ellipsoid/cylinder for bulk, runs for irregular silhouettes, repeat/mirror for symmetry, points only for small details). It does not explicitly state when to choose this tool over load_voxel_project or create_voxel_model, so it stops short of full alternative routing.

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