run_behavior_tree

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

Beyond the annotations it reveals non-obvious behavior: the search is editor-world only, PIE pawns lack auto-possession so the call typically errors with no AIController, and nothing is saved. This is exactly the kind of failure-mode context an agent needs and that annotations (readOnly=false, destructive=true, idempotent=false) cannot express.

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 core behavior and caveats are front-loaded in the first sentences, which is good. However, the return fields are stated twice ('Returns started and ai_controller' inline and then again in the Returns block), a small redundancy that costs some efficiency.

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 2-parameter mutation with no structured output schema, the description carries the full burden well: it explains what happens, the significant failure case, that state is not persisted, and enumerates the return shape. Nothing an agent needs to call it correctly appears 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 coverage is 100%, so baseline is 3, but the description adds meaning beyond the schema by clarifying that actor_name may be either the AIController or the pawn it possesses and is resolved in the editor world only (first match). That extra semantic guidance about resolution context goes beyond the schema's field-level text.

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 ('Start a BehaviorTree asset'), names the exact engine call (AAIController::RunBehaviorTree), and states the target actor type. This clearly distinguishes it from the sibling lifecycle tools (pause_behavior_tree, stop_behavior_tree, resume_behavior_tree, restart_behavior_tree) without needing to open a schema.

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 states a strong when/when-not: valid only in the editor world, never PIE, and it usually fails there because pawns are not auto-possessed. It does not name alternative tools for other contexts, but the operating constraint is explicit and actionable.

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