wm_surprise

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

No annotations are provided, so the description alone must disclose behavioral traits. It says nothing about side effects, permissions, destructive behavior, or operational impact. The label gives no behavioral insight.

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?

Extremely short (3 words) but at the cost of substance. It is under-specified rather than concise; the space is not used effectively to convey necessary information.

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 tool's complexity (nested parameter, no output schema, many siblings), the description is completely inadequate. It omits return behavior, trigger conditions, and integration context, making it nearly useless for an agent.

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?

Although schema coverage is 100%, the description adds no meaning to the parameters. It does not explain how the nested 'action' properties (targetNeurons, strengths, duration) relate to violation-of-expectation detection. The agent learns nothing beyond the schema.

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?

Description is a 3-word label ('Violation-of-Expectation Detection') that vaguely hints at purpose but lacks a verb or resource. It does not specify what the tool does (e.g., compute, detect, or return) and fails to distinguish it from siblings like wm_predict or tcai_curiosity.

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 guidance on when to use this tool versus alternatives. Without context on preconditions, expected input scenarios, or when not to use it, the agent cannot effectively select this tool.

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