remesh

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

With no annotations, the description carries the full burden and does well: it discloses destructiveness ('the old topology and UVs are lost') and a cost tradeoff (smaller voxel_size yields many more triangles). It does not mention permissions, whether the operation is reversible/undoable, or runtime cost.

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?

Three sentences, front-loaded with the core action, then the cost note, then the destructive warning and sibling routing. No filler.

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 destructive mesh-rebuild tool with no annotations and no output schema, the description covers purpose, consequences, and alternatives adequately. Minor gaps remain around smooth_shading and whether the operation is undoable.

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% with 3 parameters, so the description must compensate. It explains voxel_size semantics well (detail vs. triangle count), but says nothing about the required 'object' parameter or what smooth_shading controls, leaving two of three params undocumented.

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 and resource ('rebuild the mesh as an even voxel surface') and elaborates the effect ('fuses overlapping parts into one skin'). It explicitly distinguishes itself from the sibling operations subdivide and subdivide_faces, so an agent can route correctly without opening 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?

Names the alternatives (subdivide for rounding while keeping topology, subdivide_faces for adding geometry to picked faces) and the condition that selects each. It stops short of stating when remesh itself is the right choice (e.g. after boolean/combine or before sculpting), so it is clear but not fully prescriptive.

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