Skip to main content
Glama

Score Coherence with Leviathan Signal

leviathan_interfere
Destructive

Coherent Gate + Leviathan (PAID, x402/USDC). Fetches the SML Leviathan signal (squeeze, momentum, or all) for a ticker, adds it as one path with your optional paths and registered sources, then runs the same coherence check as interfere: consensus, coherence 0-1, pass/block gate. Same tiers and billing as interfere ($0.25 max tier charged upfront; x402 difference recorded as owed, Arc rail captures only the used tier). If Leviathan is unavailable it continues on the other paths; with no paths it errors before charging. Max 32 paths. Not financial advice.

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": {
      "ticker": "<ticker>",
      "signal_type": "<signal_type>"
    },
    "name": "leviathan_interfere"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathsNoCoherent Gate: extra signal paths (Leviathan adds one; total ≤ 32).
tickerYesTicker symbol, 1-10 uppercase letters (e.g. AAPL).
sourcesNoOptional path-source ids added alongside Leviathan; default = all enabled verified sources.
arc_auth_idNoArc rail: authId from AuthCaptureEscrow.authorize() for at least the max-tier amount to our receiver. Only the used tier is captured; the rest returns via reclaim() after expiry.
signal_typeYesWhich Leviathan signal to fetch and add as a path: squeeze, momentum, or all.
payment_headerNoBase64 X-PAYMENT EIP-3009 payload (standard rail).
wallet_addressNoAgent wallet address (informational).
payment_tx_hashNoBase USDC tx hash (sovereign rail).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / paths / items / properties / confidence / description
      Added value: +"Weight 0-1 this path gets in the consensus."
    • addedInput schema / properties / paths / items / properties / direction / description
      Added value: +"Direction this path calls: long, short, or flat."
    • addedInput schema / properties / paths / items / properties / source / description
      Added value: +"Label for where this signal came from (1-64 chars)."
    • changedInput schema / properties / signal_type / description
      Previous value: -"Leviathan engine to include as a path."New value: +"Which Leviathan signal to fetch and add as a path: squeeze, momentum, or all."
    • changedInput schema / properties / ticker / description
      Previous value: -"Ticker symbol."New value: +"Ticker symbol, 1-10 uppercase letters (e.g. AAPL)."
  2. Changed1 schema field changed
    • addedInput schema / properties / sources
      Added value: +{
      +  "description": "Optional path-source ids added alongside Leviathan; default = all enabled verified sources.",
      +  "items": {
      +    "maxLength": 64,
      +    "type": "string"
      +  },
      +  "maxItems": 16,
      +  "type": "array"
      +}
  3. Added

TDQS

A4.3/5.0
Behavior4/5

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

With destructiveHint=true and openWorldHint=true already declared, the description adds genuinely new behavioral detail: the $0.25 max-tier upfront charge, how the x402 difference is recorded as owed, that the Arc rail captures only the used tier and reclaims the rest, and the 32-path ceiling. It does not spell out irreversibility or what a failed/partial charge leaves behind, but the monetary disclosure materially exceeds 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 core action and its relation to interfere are front-loaded, and every clause carries information. The billing parenthesis is dense and parenthetical-heavy, which slows parsing slightly, but nothing is redundant.

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

Completeness4/5

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

For an 8-parameter paid tool with no output schema, the description supplies the return shape (consensus, coherence 0-1, pass/block gate), the fallback and error paths, and the payment model. Only the failure-mode behavior after a charge has been initiated remains unspecified.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema can't: why paths max out at 31 (Leviathan contributes the 32nd), what the three signal_type values do in the pipeline, and how arc_auth_id / payment_header / payment_tx_hash map to the three billing rails and their capture semantics.

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

Purpose5/5

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

The description names a specific verb chain — fetch the Leviathan signal for a ticker, append it as a path, then run the same coherence check as interfere — and explicitly differentiates itself from the 'interfere' sibling. An agent can tell exactly what this composite tool produces without opening the schema.

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

Usage Guidelines4/5

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

It gives clear operating context: use when you want a Leviathan-derived path merged with your own paths and registered sources, and it states the fallback (continues on other paths if Leviathan is unavailable) and the failure case (errors before charging when there are no paths). It stops short of explicitly saying 'use interfere instead when you don't need the Leviathan signal,' leaving the sibling choice implicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources