set_static_mesh_convex_collision

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds substantial context beyond them: existing collision is removed first, re-running replaces rather than duplicates, read-only /Engine sources are copied to dest_path, and bad input is surfaced as a clean error instead of a fake success. It also enumerates the return payload, which matters because no output schema exists.

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 main action is front-loaded in the first sentence, and the return list at the end is useful given the absent output schema. Some implementation specifics, such as the full subsystem method name and duplicate-first internals, are dense but still relevant to behavioral transparency.

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, idempotent mutation with no output schema, the description covers the key gaps: what is replaced, when duplication occurs, error conditions, and the shape of the returned data. Together with annotations covering safety hints, an agent has enough information to call it correctly.

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 parameter meanings are already documented. The description adds only minor context around dest_path's role when copying a read-only source; it does not add syntax, ranges, or defaults for hull_count, hull_precision, or max_hull_verts beyond what the schema already provides.

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: replacing a UStaticMesh's simple collision with a V-HACD convex decomposition. The contrast with 'simple collision' and the explicit editor-action alias distinguish it from siblings like add_simple_collision_to_static_mesh and set_static_mesh_kdop_collision.

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 implies when to use the tool by explaining the V-HACD/convex-decomposition purpose, but it never names an alternative collision tool or states when not to use it. It gives some operational context (read-only /Engine source is duplicated first, bad input returns false) but stops short of explicit routing guidance.

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