Skip to main content
Glama

wm_surprise

Detect violation-of-expectation events by applying targeted neuron perturbations and measuring response deviations in ASTRA spiking neural networks.

Instructions

Violation-of-Expectation Detection

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "wm_surprise"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesAction that was applied

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.1.0

TDQS

C2.3/5.0
Behavior2/5

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

Annotations already disclose that this is non-read-only, non-idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds nothing beyond that: it does not say whether this mutates network state, consumes an injected action, requires a prior encode/predict step, or returns anything. With annotations present the bar is lower, but zero added context leaves a 2.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three words with no padding, so nothing is wasted, but it is under-specified rather than concise. It is front-loaded only in the trivial sense of being a single phrase.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A tool with a nested object parameter, no output schema, and a research-heavy domain (violation-of-expectation in a world model) needs far more explanation than one phrase. The description does not explain what the action parameter represents in this context or what the agent gets back, leaving a meaningful gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so targetNeurons, strengths, and duration are already documented in the schema; the baseline is 3. The description adds no meaning about how the action object relates to surprise detection or what units/interpretation the strengths carry beyond the schema's own notes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a bare noun phrase that expands the tool name rather than stating what the tool does. There is no verb (compute, detect, report, inject) and no differentiation from siblings such as wm_predict, wm_status, or wm_train_step, so an agent cannot tell what operation 'Violation-of-Expectation Detection' performs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance is given, no prerequisites, and no reference to the many sibling world-model tools (wm_predict, wm_status, wm_plan) that an agent would need to choose between. Usage can only be inferred from the name.

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