repair_mesh_self_intersections

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

Annotations already declare destructive/not-read-only/not-idempotent, and the description goes well beyond them: it discloses convergence semantics and, critically, that the engine ignores its internal success flag and always returns the target mesh so success must be judged by triangle count. That is exactly the kind of non-obvious behavior an agent cannot get from structured fields. The only blemish is tension with idempotentHint=false, since 'a second pass ... is a no-op' reads as idempotent behavior; I read it as convergence plus a differing return value rather than a hard contradiction.

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-loaded with the action in the first sentence, then convergence, then the return-value caveat, then the explicit Returns block. Every sentence earns its place and no information is duplicated.

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?

A destructive mutation tool with no output schema, yet the description supplies the return shape, the convergence behavior, and the success-measurement caveat. Nothing an agent needs to invoke and interpret the result correctly is missing.

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% and each parameter already documents its FGeometryScriptMeshSelfUnionOptions mapping and default, so the schema carries the burden. The description adds no parameter-level meaning beyond naming the operation, so the baseline 3 is appropriate.

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 gives a specific verb+resource and scope: 'Boolean-union a DynamicMeshActor's dynamic mesh with itself to repair self-intersections, remove internal/floating geometry and resolve non-manifold overlaps.' It even names the underlying engine function, so an agent can distinguish this repair operation from siblings like apply_mesh_boolean (two-mesh boolean), weld_mesh_edges, or compact_mesh.

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 makes the problem it solves clear (self-intersections, internal/floating geometry, non-manifold overlaps), which implies when it is appropriate, but it never names an alternative or states when NOT to use it. There is no routing hint pointing to weld_mesh_edges, compact_mesh, or apply_mesh_boolean for adjacent cleanup tasks. Usage is therefore only implied, not stated.

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