Skip to main content
Glama

WaveGuard

by com.emergentphysicslab
OverviewDiscussionsAdmin

waveguard_mechanism_probe

Read-onlyIdempotent

Run targeted interventions and rank effect sizes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
trainingYes2+ baseline normal samples used to construct the reference profile.
base_testYesBaseline candidate sample before interventions.
field_levelNo0 = real scalar field, 1 = complex field.
sensitivityNoAnomaly sensitivity multiplier (default: 1.0).
encoder_typeNoOptional encoder override. Omit to auto-detect.
intervention_testsYes1+ intervention variants used to estimate effect sizes.
intervention_labelsNoOptional labels for intervention variants (same order as intervention_tests).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / base_test / description
      Added value: +"Baseline candidate sample before interventions."
    • addedInput schema / properties / encoder_type / description
      Added value: +"Optional encoder override. Omit to auto-detect."
    • addedInput schema / properties / field_level / description
      Added value: +"0 = real scalar field, 1 = complex field."
    • addedInput schema / properties / intervention_labels / description
      Added value: +"Optional labels for intervention variants (same order as intervention_tests)."
    • addedInput schema / properties / intervention_tests / description
      Added value: +"1+ intervention variants used to estimate effect sizes."
    • addedInput schema / properties / sensitivity / description
      Added value: +"Anomaly sensitivity multiplier (default: 1.0)."
    • addedInput schema / properties / training / description
      Added value: +"2+ baseline normal samples used to construct the reference profile."
  2. Added

TDQS

C2.9/5.0
Behavior2/5

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

The annotations (readOnlyHint, idempotentHint, destructiveHint) cover the safety profile, but the description adds no behavioral context beyond its stated purpose. It does not disclose how 'interventions' are executed, what is returned, or any side effects, relying entirely on the annotations.

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

Conciseness4/5

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

The description is a single efficient sentence with no wasted words. It front-loads the main action and output, but is so brief that it omits contextual detail, making it concise yet slightly under-specified.

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?

With 7 parameters, no output schema, and many siblings, the description is insufficient for an agent to fully understand what the tool does or what to expect. It lacks information about what 'interventions' mean, how effect sizes are ranked, or what the return value looks like.

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 the schema already documents all seven parameters. The description adds no parameter-level meaning, but given full schema coverage, the baseline of 3 is appropriate.

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

Purpose4/5

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

The description 'Run targeted interventions and rank effect sizes' clearly states the tool's core function with a specific verb and resource. It distinguishes the tool as an intervention/effect-size ranking operation, though it does not explicitly differentiate it from the many sibling tools.

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 usage guidance is provided. The description does not indicate when to choose this tool over siblings like waveguard_counterfactual or waveguard_cascade_risk, nor does it mention prerequisites, typical use cases, or when not to use it.

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

All WaveGuard toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources