Skip to main content
Glama

AINumbers Fintech Intelligence Suite

by co.ainumbers
OverviewDiscussionsAdmin

Cash Forecast Accuracy Scoring

score_cash_forecast_accuracy
Read-onlyIdempotent

Cash Forecast Accuracy Scoring: OpenChainGraph compute node (analytics_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: art-258-parse-camt053-reconciliation, art-261-test-hedge-effectiveness. Open at: https://ainumbers.co/chaingraph/art-263-score-cash-forecast-accuracy.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("score_cash_forecast_accuracy").

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": {
-    "afp_benchmark_tiers": {
-      "type": "string"
-    },
-    "by_horizon": {
-      "properties": {
-        "T+1": {
-          "properties": {
-            "accuracy_tier": {
-              "type": "string"
-            },
-            "bias_pct": {
-              "type": "integer"
-            },
-            "mape_pct": {
-              "type": "integer"
-            },
-            "n": {
-              "type": "integer"
-            }
-          },
-          "type": "object"
-        }
-      },
-      "type": "object"
-    },
-    "not_legal_advice": {
-      "type": "string"
-    },
-    "overall_accuracy_tier": {
-      "type": "string"
-    },
-    "overall_bias_pct": {
-      "type": "integer"
-    },
-    "overall_mape_pct": {
-      "type": "integer"
-    },
-    "persistent_sign_periods": {
-      "type": "integer"
-    },
-    "pii_note": {
-      "type": "string"
-    },
-    "regulatory_basis": {
-      "type": "string"
-    },
-    "skipped_zero_actual": {
-      "type": "integer"
-    },
-    "table_source": {
-      "type": "string"
-    },
-    "table_version": {
-      "type": "string"
-    },
-    "timing_bias_detected": {
-      "type": "boolean"
-    },
-    "total_observations": {
-      "type": "integer"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "afp_benchmark_tiers": {
+      "type": "string"
+    },
+    "by_horizon": {
+      "properties": {
+        "T+1": {
+          "properties": {
+            "accuracy_tier": {
+              "type": "string"
+            },
+            "bias_pct": {
+              "type": "integer"
+            },
+            "mape_pct": {
+              "type": "integer"
+            },
+            "n": {
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        }
+      },
+      "type": "object"
+    },
+    "not_legal_advice": {
+      "type": "string"
+    },
+    "overall_accuracy_tier": {
+      "type": "string"
+    },
+    "overall_bias_pct": {
+      "type": "integer"
+    },
+    "overall_mape_pct": {
+      "type": "integer"
+    },
+    "persistent_sign_periods": {
+      "type": "integer"
+    },
+    "pii_note": {
+      "type": "string"
+    },
+    "regulatory_basis": {
+      "type": "string"
+    },
+    "skipped_zero_actual": {
+      "type": "integer"
+    },
+    "table_source": {
+      "type": "string"
+    },
+    "table_version": {
+      "type": "string"
+    },
+    "timing_bias_detected": {
+      "type": "boolean"
+    },
+    "total_observations": {
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}
  3. Added

TDQS

C2.9/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive, yet the description adds real behavioral facts: deterministic execution, transient processing with no storage/logging/retention, synthetic-inputs-only policy, compute-mode routing including browser delegation URLs, and an AP2 artifact with execution_hash for provenance. It does not describe the returned payload, but it points to describe_tool for that.

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 description is dominated by infrastructure boilerplate (kernel registration, Cloudflare Workers, FV-status hash URL, chain provenance) that does little to help tool selection. The functional purpose is buried after a title restatement, and the FV-status snapshot sentence is particularly low-value for an invoking agent.

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

Completeness3/5

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

Chaining inputs, data-handling policy, and artifact provenance are covered, and output shape is delegated to describe_tool, so the core is present. However, for a scoring tool the description never indicates what the decision function consumes or how the forecast/actual series should be supplied through policy_parameters, leaving the calling contract opaque.

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 baseline is 3. The description's compute-mode explanation duplicates what the schema already states for the compute enum, and policy_parameters is explicitly deferred to 'the tool's manifest' rather than clarified, so no value is added beyond structured fields.

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

Purpose3/5

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

The first clause restates the title, and the rest identifies the node class (analytics_mandate compute node) and infrastructure behavior, but never says what 'accuracy scoring' actually computes (e.g. MAPE/bias/RMSE) or what inputs it expects. It also fails to distinguish itself from the near-identical sibling compute_forecast_accuracy_score. Purpose is inferable from the name but not elaborated.

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?

There is no explicit when-to-use, when-not-to-use, or named alternative, which matters given the sibling compute_forecast_accuracy_score. The only usable context is the list of upstream artifacts it consumes (art-258 parse_camt053_reconciliation, art-261 test_hedge_effectiveness), which implies sequencing but is never framed as guidance.

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