wm_surprise

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It only states 'Violation-of-Expectation Detection' without revealing whether the tool is read-only, whether it modifies working memory state, whether it requires prior actions, what it returns, or any side effects. This is a near-total behavioral black box.

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 short, but under-specification is not conciseness. It is a single label with no structure or elaboration. While front-loaded, it does not earn its place because it fails to convey operational details needed by an agent.

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, no annotations, and a nested input schema, the description needs to explain the invocation context, return values, and behavioral effects. It supplies none of this. An agent cannot determine what will happen when calling the tool or how to interpret the result, making the description inadequate for a tool of this complexity.

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 covers all parameters with descriptions, including the nested 'action' object and its properties (targetNeurons, strengths, duration). Since schema description coverage is 100%, the baseline is 3. The tool description itself adds no extra meaning about how these parameters relate to surprise detection, but no parameter is left undocumented.

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 noun phrase that essentially restates the tool name: 'wm_surprise' is defined as 'Violation-of-Expectation Detection'. It lacks a clear verb+resource structure and does not explain what specific operation is performed (detect, report, update, etc.). It also does not distinguish the tool from sibling working-memory tools like wm_predict 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?

No guidance is provided about when to use this tool versus alternatives. The description does not mention any context, prerequisites, or exclusions. Sibling tools like wm_encode, wm_predict, and wm_plan could overlap in purpose, but no usage direction is given.

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