ue_world

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

With no annotations, the description carries the full burden; it does add real value by disclosing that spawn validates friendly class names and refuses unresolvable ones, and that set_transform reads back the landed transform. However, it is silent on the destructive nature of delete, on any permissions or editor-connection requirements, and on level_streaming side effects.

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?

Purpose is front-loaded, followed by the action enumeration and then two behavioral caveats; there is no filler. The long slash-delimited action run-on is dense but functional rather than wasteful.

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 single dispatcher covering ~16 actions with 7 parameters, a nested params object, no annotations, and no output schema needs a per-action parameter contract that this description does not provide. An agent can identify the tool but cannot reliably determine which parameters each action requires or what state it mutates.

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 largely does not: the 'params' object is never mentioned, and the mapping of location/rotation/scale to specific actions is only hinted via set_transform. The note about actor_class resolving to /Script/Engine.* is the one genuine semantic addition.

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?

Names the resource precisely ('scene actors on the editor side') and enumerates the specific operations it dispatches (spawn, duplicate, attach, set_lighting, level_streaming, etc.), so an agent knows this is the actor/level-manipulation entry point. It does not explicitly contrast itself with siblings like ue_blueprint or ue_material, but the actor-scoped framing does most of the disambiguation work.

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 action list implies when to reach for this tool, but there is no explicit 'use this when / use X instead' guidance and no routing to ue_blueprint, ue_material, or ue_status. An agent must infer from the action vocabulary which requests belong here versus a sibling tool.

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