recompute_mesh_normals

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

With annotations already declaring readOnlyHint=false, destructiveHint=true, and idempotentHint=true, the description adds rich context beyond them: it overwrites the existing normal overlay while preserving hard-edge splits, operates in an editor transaction with nothing saved, is idempotent, and errors on an empty mesh or when recomputed=false is returned. This gives the agent a clear picture of mutability, persistence, and failure behavior.

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 operation, then adds weighting, transactional behavior, error conditions, usage guidance, and a return shape. Every sentence contributes useful information for calling the tool correctly, with no filler or repetition beyond what is necessary.

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?

Although there is no output schema, the description supplies the return object structure directly. Combined with annotations covering the safety profile and the schema covering all parameters, the description leaves no significant gap about what the tool does, how its parameters interact, when to use it, and what it returns.

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 schema already documents each parameter and the baseline is 3. The description adds meaningful interaction semantics by explaining that area and angle weighting are both on by default and that turning both off yields a plain average, which is not stated in the schema.

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 (recompute) and resource (normals of the live dynamic mesh of a DynamicMeshActor in the editor world), and clarifies scope by mentioning the existing normal overlay, hard-edge splits, and behavior for meshes without normals. It also distinguishes from the related copy_dynamic_mesh_to_static_mesh sibling by noting that tool persists the result, making the boundary between editing and saving explicit.

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?

It provides clear context for use: 'Use it when shading looks wrong after geometry edits' and names copy_dynamic_mesh_to_static_mesh as the way to persist the result. However, it does not explicitly state when not to use this tool or name a direct alternative for the same recompute purpose, so it falls just short of the highest bar.

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