repair_mesh

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses each repair operation, which parameters skip behavior, what happens to empty material slot faces, which defect types are not repaired ('non_manifold_edges ... not repaired'), and the exact shape of the returned removal/count data.

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?

The description is front-loaded with the core purpose and is information-dense without filler. However, it is a single long, clause-heavy sentence that could be easier to scan if broken into a list or shorter sentences.

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?

Given no output schema, no annotations, and 8 parameters, the description is complete enough for an agent: it explains the repair operations, parameter effects, return payload, and a concrete usage context. The only minor omission is an explicit description of the required object parameter, but the meaning is clear from context.

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 for nearly every parameter: weld scaling and zero/empty behavior, hole_sides meaning and 0 special case, fill_holes=false skipping, the effect of remove_empty_slots, and the boolean toggles for dissolve_degenerate and remove_loose. The required 'object' parameter is only implied by 'one mesh' rather than explicitly defined.

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 states a specific verb and resource: 'Heal one mesh in place,' followed by an explicit list of repair operations. It distinguishes itself from narrower siblings like weld and check_mesh by being a comprehensive, in-place mesh repair tool, and it even names a specific use case (before boolean).

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 provides clear context for when to use it: 'Run it before boolean on parts you cut or joined by hand.' It does not, however, name specific alternatives to use instead in other situations, nor does it state when not to use this tool.

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