wm_train_step

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

No annotations exist, so the description must fully disclose behavior. However, it only states 'Online World Model Training Step' without mentioning any side effects, state changes, safety concerns, or what the action injection actually does to the model. Critical information about destructiveness or mutation is omitted.

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 description is extremely brief (one phrase) but fails to convey essential information. It does not earn its place because it does not provide utility to the agent; it is under-specified rather than concise.

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?

Given the nested parameter structure and the tool's role in a world model training sequence, the description is completely inadequate. It lacks any explanation of training context, return behavior, or integration with other tools. The absence of an output schema further compounds the incompleteness.

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?

The single parameter 'action' is fully described in the schema with property descriptions (targetNeurons, strengths, duration). Since schema coverage is 100%, the description adds no extra meaning but does not detract. The baseline of 3 is appropriate.

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 is a short phrase 'Online World Model Training Step' which vaguely indicates a training operation but doesn't specify what the tool actually accomplishes. It fails to distinguish itself from sibling tools like wm_encode or wm_plan, and doesn't explain the role of the action parameter in training.

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 provides no guidance on when to use this tool, what prerequisites are needed, or how it relates to other world model tools. The agent receives no context about whether to call this before or after other steps, or what conditions warrant training.

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