AINumbers Fintech Intelligence Suite

CECL Expected Credit Loss & Allowance Calculator

calculate_cecl_ecl_allowance

Read-onlyIdempotent

CECL Expected Credit Loss & Allowance Calculator: OpenChainGraph compute node (credit_assessment). 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. Open at: https://ainumbers.co/chaingraph/art-426-cecl-ecl-calculator.html FV-status (published/proven/still-trusted for this spec): /fv-status/ca4e1dca8343f788a296161f0e19712f7afb7e5eaec0431081e715a4cc34b784.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched. Summary: Computes a deterministic CECL (Current Expected Credit Loss, ASC 326) allowance given caller-supplied PD/LGD/EAD curves, segment exposures, and forecast scenario weights, and reconciles the result against the prior period's allowance balance. Outputs: boundary_note, charge_offs_usd, constants_version, delta_vs_required_usd, disambiguation, forecast_weights, method, prior_allowance_balance_usd, provision_expense_usd, reconciled_ending_allowance_usd, reconciliation_balanced, recoveries_usd, segment_count, segments, total_required_allowance_usd. Output schema: call describe_tool("calculate_cecl_ecl_allowance").

Input Schema

Name	Required	Description
`compute`	No	Compute 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_hashes`	No	execution_hash values from upstream ChainGraph AP2 artifacts to chain from (sets chain.parent_hashes in the export).
`parent_tool_ids`	No	tool_id values matching parent_hashes, in the same order.
`policy_parameters`	No	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". Required: constants_version, forecast_weights, method, segments. Unknown keys are refused.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 22, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Changed3 schema fields changedOct 19, 2026

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\". Required: constants_version, forecast_weights, method, segments. Unknown keys are refused."

addedInput schema / properties / policy_parameters / properties

Added value: +{
+  "charge_offs_usd": {
+    "type": "number"
+  },
+  "constants_version": {},
+  "forecast_weights": {
+    "type": "array"
+  },
+  "method": {},
+  "prior_allowance_balance_usd": {
+    "type": "number"
+  },
+  "recoveries_usd": {
+    "type": "number"
+  },
+  "segments": {
+    "type": "array"
+  }
+}

removedInput schema / properties / policy_parameters / propertyNames
```
Removed value: -{
-  "type": "string"
-}
```

Changed1 schema field changedSep 18, 2026

changedOutput schema / (root)

Previous value: -{
-  "properties": {
-    "boundary_note": {
-      "type": "string"
-    },
-    "charge_offs_usd": {
-      "type": "integer"
-    },
-    "constants_version": {
-      "type": "string"
-    },
-    "delta_vs_required_usd": {
-      "type": "integer"
-    },
-    "disambiguation": {
-      "type": "string"
-    },
-    "forecast_weights": {
-      "items": {
-        "properties": {
-          "scenario": {
-            "type": "string"
-          },
-          "weight": {
-            "type": "number"
-          }
-        },
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "method": {
-      "type": "string"
-    },
-    "prior_allowance_balance_usd": {
-      "type": "integer"
-    },
-    "provision_expense_usd": {
-      "type": "integer"
-    },
-    "reconciled_ending_allowance_usd": {
-      "type": "integer"
-    },
-    "reconciliation_balanced": {
-      "type": "boolean"
-    },
-    "recoveries_usd": {
-      "type": "integer"
-    },
-    "segment_count": {
-      "type": "integer"
-    },
-    "segments": {
-      "items": {
-        "properties": {
-          "ead_usd": {
-            "type": "integer"
-          },
-          "exposure_balance_usd": {
-            "type": "integer"
-          },
-          "lgd_pct": {
-            "type": "integer"
-          },
-          "remaining_life_years": {
-            "type": "integer"
-          },
-          "scenario_count": {
-            "type": "integer"
-          },
-          "scenarios": {
-            "items": {
-              "properties": {
-                "scenario": {
-                  "type": "string"
-                },
-                "scenario_ecl_usd": {
-                  "type": "integer"
-                },
-                "weight": {
-                  "type": "number"
-                }
-              },
-              "type": "object"
-            },
-            "type": "array"
-          },
-          "segment_ecl_usd": {
-            "type": "integer"
-          },
-          "segment_id": {
-            "type": "string"
-          }
-        },
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "total_required_allowance_usd": {
-      "type": "integer"
-    }
-  },
-  "type": "object"
-}New value: +null

Changed1 schema field changedSep 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "boundary_note": {
+      "type": "string"
+    },
+    "charge_offs_usd": {
+      "type": "integer"
+    },
+    "constants_version": {
+      "type": "string"
+    },
+    "delta_vs_required_usd": {
+      "type": "integer"
+    },
+    "disambiguation": {
+      "type": "string"
+    },
+    "forecast_weights": {
+      "items": {
+        "properties": {
+          "scenario": {
+            "type": "string"
+          },
+          "weight": {
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "method": {
+      "type": "string"
+    },
+    "prior_allowance_balance_usd": {
+      "type": "integer"
+    },
+    "provision_expense_usd": {
+      "type": "integer"
+    },
+    "reconciled_ending_allowance_usd": {
+      "type": "integer"
+    },
+    "reconciliation_balanced": {
+      "type": "boolean"
+    },
+    "recoveries_usd": {
+      "type": "integer"
+    },
+    "segment_count": {
+      "type": "integer"
+    },
+    "segments": {
+      "items": {
+        "properties": {
+          "ead_usd": {
+            "type": "integer"
+          },
+          "exposure_balance_usd": {
+            "type": "integer"
+          },
+          "lgd_pct": {
+            "type": "integer"
+          },
+          "remaining_life_years": {
+            "type": "integer"
+          },
+          "scenario_count": {
+            "type": "integer"
+          },
+          "scenarios": {
+            "items": {
+              "properties": {
+                "scenario": {
+                  "type": "string"
+                },
+                "scenario_ecl_usd": {
+                  "type": "integer"
+                },
+                "weight": {
+                  "type": "number"
+                }
+              },
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "segment_ecl_usd": {
+            "type": "integer"
+          },
+          "segment_id": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total_required_allowance_usd": {
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}

AddedJul 24, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world. The description adds genuinely non-obvious behavior: deterministic kernel execution on Cloudflare Workers, transient processing with no storage or logging, an exported AP2 artifact carrying execution_hash for chain provenance, and an offline-verifiable FV-status snapshot. It does not describe failure modes or what 'boundary_note' or 'reconciliation_balanced' signal when they fail.

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?

Roughly two-thirds of the text is platform boilerplate (compute binding, privacy, artifact export, a URL, and a 64-character FV-status path) that precedes the actual purpose, which arrives only in the final sentence. The what-it-does statement an agent needs first is buried last, and the raw hash path adds noise without decision value.

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?

With no output schema, the description compensates by enumerating the full output field list (reconciled_ending_allowance_usd, provision_expense_usd, reconciliation_balanced, segments, etc.), which is the key missing structured data. For a nested four-parameter compute node it covers inputs, execution semantics, and returns adequately; only error/failure behavior and the required-vs-optional treatment of nested policy fields are thin.

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% at the top level, which sets the baseline at 3, and the compute/parent_hashes prose largely repeats the schema text. The description does add real meaning for the nested policy_parameters block, whose members (method, segments, forecast_weights, constants_version) carry no type or description in the schema, by naming PD/LGD/EAD curves, segment exposures, and forecast weights.

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 specific verb and resource: 'Computes a deterministic CECL (Current Expected Credit Loss, ASC 326) allowance given caller-supplied PD/LGD/EAD curves, segment exposures, and forecast scenario weights, and reconciles the result against the prior period's allowance balance.' That is far more specific than the title restated. It does not, however, name any sibling (e.g. score_credit_default_risk, calculate_rwa_scenarios) or state how it differs from them.

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 only selection guidance is about compute mode ('auto' vs 'browser' vs gpu:true delegation) and an input constraint ('Use synthetic or anonymised inputs only'). There is no statement of when to reach for this calculator versus the many other credit/allowance tools in the sibling list, so the fit has to 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.

All AINumbers Fintech Intelligence Suite tools Inspect

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.

CECL Expected Credit Loss & Allowance Calculator

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources