wm_train_step

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

No annotations are provided, so the description must fully disclose behavioral traits. It does not mention whether the tool mutates the model, what side effects occur, if it requires prior observations, or whether it is a training step that adjusts weights. The description is completely opaque.

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 a single nominal phrase and contains no redundant words, but it is severely under-specified. This is not conciseness but lack of information, matching the calibration for under-specification.

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?

The tool involves a nested action object and represents a training step, yet the description provides no elaboration on the training process, expected outcomes, or preconditions. Without annotations or an output schema, this is completely inadequate for safe invocation.

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 schema provides descriptions for 'action', 'targetNeurons', 'strengths', and 'duration' (100% coverage). The tool description adds no further meaning to these parameters, but because the schema already covers them, 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 'Online World Model Training Step' is essentially a restatement of the tool name 'wm_train_step'. It fails to specify what action the tool performs (e.g., 'Trains the world model on a given action') and does not distinguish itself from sibling training-related tools like wm_encode or wm_predict. The purpose is only vaguely implied.

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 guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites, or relationships to sibling tools such as wm_predict or wm_surprise, leaving the agent without context for appropriate selection.

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