mesh_operation

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

With no annotations, the description carries the full burden and does substantial work: it discloses that results are written as new STL files into a new directory, that a measured result/checkpoint is produced, that units are assumed millimeters, and that reimporting into Orca loses settings and facet painting. It still doesn't say whether source files are modified or how failures are surfaced.

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?

Very dense, front-loaded with the action list followed by the parameters that matter most; every line carries information. The telegraphic phrasing ('action convex_hull for hull') is occasionally terse enough to need a second read, but there is essentially 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?

An output schema exists, so return values need not be spelled out, yet the description still notes the measured result/checkpoint. Combined with format, units, and the Orca reimport caveat, it covers what an agent needs to invoke correctly; the missing piece is whether sources are mutated.

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 coverage is 0%, so the description must compensate, and it largely does: it gives the sources shape `[{path,sha256}]`, maps per-action options (convex_hull, cut's origin/normal vectors and optional cap, simplify's face_count, transform's 4x4 column-vector affine matrix), and implies destination_directory is where the new directory is written. Actions like repair/split/merge have no parameter detail, leaving gaps.

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 opens with a concrete verb list scoped to a resource: 'Offline mesh repair/split/cut/merge/union/difference/intersection/hull/simplify/transform.' That enumerates the operation surface clearly. It doesn't name sibling tools (mesh_inspect, project_transform_write, native_transform) as alternatives, so differentiation beyond scope is left implicit.

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?

Usage is implied rather than stated: 'Offline' plus 'outputs new STL files' signals a non-destructive, file-based workflow, and 'Requires [geometry]' hints at a gating precondition. There is no explicit when-to-use/when-not guidance versus mesh_inspect or project_transform_write, and no statement of prerequisites like existing destination directory.

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