wm_predict

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

With no annotations, the description must fully disclose behavior, but it only states the outcome (predict next state) without clarifying side effects, read-only nature, or what happens to the system state during prediction.

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 sentence, which is concise but lacks structure. It could include more details in a front-loaded manner without adding length, but it is minimally adequate.

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 complexity (nested object, no output schema) and the lack of behavior details, the description is insufficient. It does not explain return values, error conditions, or how the prediction output can be used.

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 the schema already documents both parameters. The description adds no extra semantics beyond the tool's purpose, maintaining the baseline score without enhancement.

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 tool name 'wm_predict' combined with the description 'Predict Next SNN State in Latent Space' clearly specifies the action (predict) and the resource (next SNN state) with a specific domain (latent space). This distinguishes it from sibling tools like 'wm_encode' or 'wm_plan'.

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 does not provide any guidance on when to use this tool versus alternatives, such as 'wm_surprise' or 'wm_train_step'. There is no mention of prerequisites or context for prediction.

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