wm_predict

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It only states 'Predict', which implies a non-mutating operation, but does not clarify whether it requires prior encoding, whether it has side effects, or what the output format is. 'In Latent Space' adds minimal context but not enough.

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 7-word sentence with no filler or redundancy. It front-loads the primary verb and object, achieving maximum efficiency. This is a model of conciseness.

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 and no annotations, the description should explain what the tool returns, preconditions, and how the action affects the prediction. It provides only a high-level phrase, leaving the agent to guess at critical behavioral details. The rich schema helps but cannot compensate for the absence of output and usage context.

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 input schema provides full descriptions for both parameters ('steps' as 'Number of prediction steps (rollout)' and 'action' as 'Spike injection action to condition prediction on'), so schema coverage is 100%. The description itself adds no parameter details, but the baseline score of 3 is appropriate given the schema's completeness.

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 uses a specific verb 'Predict' and names a specific resource 'Next SNN State in Latent Space', making the core action clear. However, it does not explicitly distinguish itself from sibling tools like wm_plan or snn_step, which could also involve prediction.

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?

No usage context is provided. The description gives no indication of when to use this tool versus alternatives like snn_step or inject_spikes, nor does it mention that prediction is conditioned on the 'action' parameter.

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