Skip to main content
Glama

AINumbers Fintech Intelligence Suite

by co.ainumbers
OverviewDiscussionsAdmin

Supervisory Scenario Replay (DFAST-lite)

replay_supervisory_scenario
Read-onlyIdempotent

Supervisory Scenario Replay (DFAST-lite): OpenChainGraph compute node (capital_assessment). Regulatory deadline: 2027-02-01 (Annual re-pin — Fed publishes new supervisory scenarios each February). 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. Output feeds: sim-01-lcr-nsfr-liquidity-stress-test, sim-03-basel-rwa-scenario-modeler. Open at: https://ainumbers.co/chaingraph/art-370-supervisory-scenario-replay.html FV-status (published/proven/still-trusted for this spec): /fv-status/8498d0819c941fdb731f9e10f5d93ee929026919cb111a42149821b48b5ac180.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched. Output schema: call describe_tool("replay_supervisory_scenario").

Input Schema

TableJSON 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". See the tool's manifest for field names.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "ending_capital_mn": {
-      "type": "number"
-    },
-    "not_a_submission": {
-      "type": "string"
-    },
-    "quarters": {
-      "items": {
-        "properties": {
-          "capital_mn": {
-            "type": "number"
-          },
-          "capital_ratio_pct": {
-            "type": "number"
-          },
-          "date": {
-            "type": "string"
-          },
-          "loss_mn": {
-            "type": "integer"
-          },
-          "net_income_mn": {
-            "type": "number"
-          },
-          "ppnr_mn": {
-            "type": "number"
-          },
-          "pretax_income_mn": {
-            "type": "number"
-          }
-        },
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "scenario": {
-      "type": "string"
-    },
-    "scenario_release_date": {
-      "type": "string"
-    },
-    "scenario_set_digest": {
-      "type": "string"
-    },
-    "scenario_source_url": {
-      "type": "string"
-    },
-    "starting_capital_mn": {
-      "type": "integer"
-    },
-    "trough_capital_mn": {
-      "type": "integer"
-    },
-    "trough_capital_ratio_pct": {
-      "type": "number"
-    },
-    "trough_quarter": {
-      "type": "string"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "ending_capital_mn": {
+      "type": "number"
+    },
+    "not_a_submission": {
+      "type": "string"
+    },
+    "quarters": {
+      "items": {
+        "properties": {
+          "capital_mn": {
+            "type": "number"
+          },
+          "capital_ratio_pct": {
+            "type": "number"
+          },
+          "date": {
+            "type": "string"
+          },
+          "loss_mn": {
+            "type": "integer"
+          },
+          "net_income_mn": {
+            "type": "number"
+          },
+          "ppnr_mn": {
+            "type": "number"
+          },
+          "pretax_income_mn": {
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "scenario": {
+      "type": "string"
+    },
+    "scenario_release_date": {
+      "type": "string"
+    },
+    "scenario_set_digest": {
+      "type": "string"
+    },
+    "scenario_source_url": {
+      "type": "string"
+    },
+    "starting_capital_mn": {
+      "type": "integer"
+    },
+    "trough_capital_mn": {
+      "type": "integer"
+    },
+    "trough_capital_ratio_pct": {
+      "type": "number"
+    },
+    "trough_quarter": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  3. Added

TDQS

A3.5/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing the compute routing logic (auto/server/browser, gpu:true always delegates), transient processing with no storage/logging, the AP2 artifact with execution_hash, and the FV-status receipt semantics. This is exactly the kind of context annotations (readOnly/idempotent) cannot carry. It loses a point because the description does not explain what the tool returns when it delegates to a browser URL versus computing server-side.

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?

Severely front-loaded with a federal deadline, an FV-status hash URL, a full URL, and offline-verification caveats before the actual function is described. The FV-status hash and page URL are operational noise that crowd out the value proposition, and the structure reads like a compliance banner rather than a tool definition.

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 a four-parameter read-only compute node with no output schema, the description covers compute routing, privacy posture, chaining, artifact export, and downstream consumers, which is substantial. It just stops short of describing the shape of the returned artifact or what happens on browser delegation, which would fully complete the picture.

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 coverage is 100%, so the schema already documents all four parameters including the compute enum and parent_hashes chaining. The description reinforces the compute-mode default and the chaining purpose, but adds no syntax or format detail beyond the schema. Baseline 3 applies.

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?

Names a specific verb (Replay) and resource (Supervisory Scenario Replay / DFAST-lite) and states it is a capital_assessment compute node, which differentiates it from its siblings. However, the core purpose is buried under a wall of operational metadata (deadline, compute mode, FV-status), so an agent must read past a lot of noise before it understands what the tool actually computes.

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 names downstream consumers (sim-01-lcr-nsfr-liquidity-stress-test, sim-03-basel-rwa-scenario-modeler) implying it feeds a scenario pipeline, and mentions synthetic/anonymised inputs. But it never states when to use this tool versus the many other capital/stress-test siblings (compute_stress_test_scenarios, compute_rwa_scenarios), leaving usage largely inferred.

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

All AINumbers Fintech Intelligence Suite 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