Skip to main content
Glama

AINumbers Fintech Intelligence Suite

Halt + Staleness Collateral Haircut

compute_stock_token_collateral_haircut
Read-onlyIdempotent

Halt + Staleness Collateral Haircut: OpenChainGraph compute node (collateral_mandate). Deterministic OpenChainGraph compute node. By default (compute:"auto") inputs are computed server-side on Cloudflare Workers for gpu:false nodes with a registered kernel; compute:"browser" forces client-side execution and returns a browser delegation URL instead. gpu:true nodes always delegate to the browser. Inputs are processed transiently to compute the response and are not stored, logged, or retained. Use synthetic or anonymised inputs only. Exports an AP2 artifact with execution_hash for chain provenance. Consumes upstream artifacts from: 505-tokenized-collateral-eligibility-checker, 508-repo-haircut-collateral-calculator. Open at: https://ainumbers.co/chaingraph/art-320-rhc-collateral-haircut.html FV-status (published/proven/still-trusted for this spec): /fv-status/565f2dd45a55e0ff0f8dafde8c1080f9e1484b32a5aaa96f4d7739a236b9258a.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched. Summary: Layers a feed-staleness, sequencer-downtime, and underlying-halt haircut on top of a base repo haircut for Robinhood Chain stock tokens posted as collateral. Outputs: adjusted_collateral_value, base_haircut, extra_haircut, feed_stale, final_haircut, liquidation_risk, sequencer_down_grace_expired, sequencer_down_within_grace, underlying_halted, verdict. Output schema: call describe_tool("compute_stock_token_collateral_haircut").

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "compute_stock_token_collateral_haircut"
  }
}

Input Schema

NameRequiredDescriptionDefault
computeNoCompute mode (v0.4 Compute Binding). "auto" (default) = server for gpu:false nodes with registered kernels; "server" = force server-side; "browser" = always return browser delegation URL. gpu:true nodes always delegate.
parent_hashesNoexecution_hash values from upstream ChainGraph AP2 artifacts to chain from (sets chain.parent_hashes in the export).
parent_tool_idsNotool_id values matching parent_hashes, in the same order.
policy_parametersNoInput parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is "auto" or "server". Unknown keys are refused.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed3 schema fields changed
    • changedInput schema / properties / policy_parameters / description
      Previous value: -"Input parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is \"auto\" or \"server\". See the tool's manifest for field names."New value: +"Input parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is \"auto\" or \"server\". Unknown keys are refused."
    • addedInput schema / properties / policy_parameters / properties
      Added value: +{
      +  "base_haircut": {},
      +  "current_time": {},
      +  "feed_round": {},
      +  "position_value": {},
      +  "sequencer_uptime": {},
      +  "underlying_market_state": {}
      +}
    • removedInput schema / properties / policy_parameters / propertyNames
      Removed value: -{
      -  "type": "string"
      -}
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "adjusted_collateral_value": {
      -      "type": "integer"
      -    },
      -    "base_haircut": {
      -      "type": "number"
      -    },
      -    "extra_haircut": {
      -      "type": "integer"
      -    },
      -    "feed_stale": {
      -      "type": "boolean"
      -    },
      -    "final_haircut": {
      -      "type": "number"
      -    },
      -    "liquidation_risk": {
      -      "type": "string"
      -    },
      -    "sequencer_down_grace_expired": {
      -      "type": "boolean"
      -    },
      -    "sequencer_down_within_grace": {
      -      "type": "boolean"
      -    },
      -    "underlying_halted": {
      -      "type": "boolean"
      -    },
      -    "verdict": {
      -      "type": "string"
      -    }
      -  },
      -  "type": "object"
      -}New value: +null
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "adjusted_collateral_value": {
      +      "type": "integer"
      +    },
      +    "base_haircut": {
      +      "type": "number"
      +    },
      +    "extra_haircut": {
      +      "type": "integer"
      +    },
      +    "feed_stale": {
      +      "type": "boolean"
      +    },
      +    "final_haircut": {
      +      "type": "number"
      +    },
      +    "liquidation_risk": {
      +      "type": "string"
      +    },
      +    "sequencer_down_grace_expired": {
      +      "type": "boolean"
      +    },
      +    "sequencer_down_within_grace": {
      +      "type": "boolean"
      +    },
      +    "underlying_halted": {
      +      "type": "boolean"
      +    },
      +    "verdict": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  5. Added

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent and non-destructive, so the extra disclosure here is real value: deterministic execution, transient processing with no storage/logging/retention, mandatory synthetic inputs, and export of an AP2 artifact carrying execution_hash for chain provenance. It also flags that the FV-status receipt is a point-in-time snapshot verifying offline. It does not describe failure or refusal behavior (e.g. 'Unknown keys are refused'), which is left to the schema.

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

Conciseness2/5

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

The definition is bloated and poorly front-loaded: 'Deterministic OpenChainGraph compute node' appears twice, a full 64-character FV-status URL fragment and hash consume a long clause, and the sentence that actually explains what the tool computes is buried under a 'Summary:' label near the end. Boilerplate about AP2 exports and offline receipts crowds out the decision-relevant content.

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?

Given there is no output schema, the description compensates well by enumerating all eleven output fields (adjusted_collateral_value, final_haircut, liquidation_risk, verdict, etc.) and by naming the upstream dependencies needed to build the chain. A caller has enough to invoke it and interpret the result, with only the per-parameter formats left implicit.

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?

With 100% schema description coverage the baseline is 3, and the description largely restates the compute-mode semantics already documented in the schema. It does add conceptual meaning for the undocumented nested policy_parameters (feed-staleness maps to feed_round/current_time, sequencer-downtime to sequencer_uptime, underlying-halt to underlying_market_state), but it never explains chaining order for parent_hashes/parent_tool_ids beyond the schema text.

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 summary sentence gives a concrete verb and resource: it layers feed-staleness, sequencer-downtime and underlying-halt haircuts on top of a base repo haircut for Robinhood Chain stock tokens used as collateral, and it names the upstream artifacts (505-tokenized-collateral-eligibility-checker, 508-repo-haircut-collateral-calculator) it extends. This is enough to separate it from generic haircut calculators, though it never explicitly says 'use calculate_repo_haircut for the base haircut first'.

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

Usage Guidelines3/5

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

The description establishes prerequisites (must chain from the 505/508 upstream artifacts) and a data-handling rule ('Use synthetic or anonymised inputs only'), plus compute mode selection between auto/server/browser. What is missing is explicit routing: no statement of when a caller should choose this node over the sibling base-haircut or eligibility tools, or when the tool is inappropriate.

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.