unreal_probe_actor

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

With no annotations, the description carries the full disclosure burden and does reveal the key safety trait ('READ-ONLY'), the matching semantics (label OR class, case-insensitive), and the display-name convention. However, it glosses over the fact that 'load a map' can disrupt the current editor session, and it never mentions the 420s default timeout, the maxActors=5 truncation, or dryRun behavior — significant behavioral traits for an agent deciding whether to call this.

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?

Two sentences, front-loaded with the safety prefix and verb+resource before any detail. The second sentence's anecdote is slightly loose ('tool shape that found...') but earns its place by evoking the output behavior (surfaceing nulls), so there's no real waste.

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 no-annotation, no-output-schema tool with 7 parameters, it covers purpose, matching semantics, and naming semantics but omits the return shape and the behavior of four optional params. An agent cannot predict whether results come as a per-actor map of requested props, how missing props surface, or how long a call may run — material gaps for a tool whose default timeout is 7 minutes.

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 only 29%, and the description genuinely compensates for the two opaque required params: props are 'editor display names' with examples, and actorMatch matches label OR class case-insensitively. But dryRun, maxActors, timeoutSeconds, and allowWithEditorOpen are documented in neither the schema nor the description, and the last one encodes a non-obvious editor-state interaction.

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+resource with method: 'load a map and read actor properties by their editor display names', backed by concrete examples ('Use Auroras', 'Ultra Dynamic Weather'). The 'READ-ONLY' prefix and 'read back the ACTUAL state' wording clearly distinguish it from write-oriented siblings such as unreal_set_actor_properties and unreal_spawn_actors.

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?

Provides a clear context for when to use it — 'read back the ACTUAL state instead of trusting push logs' — pointing at verification-after-pply scenarios, reinforced by the anecdote about finding a dead switch and null reference. It stops short of a 5 because it never explicitly names an alternative tool or states when-not-to-use.

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