create_behavior_tree

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

Annotations already declare this is a non-read-only, non-destructive, non-open-world, non-idempotent operation, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the asset is both created and saved to disk, and the return signals already_exists and a save_error, telling the agent how to detect collision and failure. Mild tension with idempotentHint=false, since already_exists implies repeat calls are detected rather than blindly re-created, but this is not a clear 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, then the return contract, with no filler sentences. The inline return object is slightly dense for a description field but is justified because no output schema exists.

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?

With no output schema, describing the returned keys (including blackboard_asset, already_exists, saved, save_error) fills a real gap and is the most valuable content here. What is missing is the failure/prerequisite side: whether a missing blackboard path fails, and what happens on name collision.

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 name, package_path and blackboard_path are already documented including defaults and an example. The description only restates the optional blackboard binding at a high level, adding no syntax or format detail beyond the schema; baseline 3 applies.

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: create and save a new UBehaviorTree asset, with the optional blackboard binding called out. It is clearly distinguishable from read-side siblings like get_behavior_tree_info or set_behavior_tree_root, but it never names or contrasts those siblings explicitly.

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?

There is no when-to-use guidance, no prerequisites (for example that the referenced UBlackboardData must already exist, likely via create_blackboard_data), and no statement of what happens when an asset of that name already exists. The agent must infer all call conditions itself.

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