AINumbers Fintech Intelligence Suite

TMPG Fails-Charge Recompute

recompute_tmpg_fails_charge

Read-onlyIdempotent

TMPG Fails-Charge Recompute: OpenChainGraph compute node (compliance_control). 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-575-tmpg-fails-charge-recompute.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: Recomputes the NY Fed Treasury Market Practices Group fails-charge claim a buyer presents to a failing seller on a UST, agency, or agency-MBS settlement fail: charge = max(0, 3% minus the caller-declared reference rate) / 360 x par amount x days failed, per the published trading practice (2016 re... Outputs: clause_note, decision, determinations, diff_tolerance_minor, fail_count, rejected_inputs, scope_note, total_claimed_charge_minor, total_recomputed_charge_minor, verdict. Output schema: call describe_tool("recompute_tmpg_fails_charge").

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: diff_tolerance_minor, fails. 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: diff_tolerance_minor, fails. Unknown keys are refused."

addedInput schema / properties / policy_parameters / properties

Added value: +{
+  "diff_tolerance_minor": {},
+  "fails": {
+    "type": "array"
+  }
+}

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

Changed1 schema field changedSep 18, 2026

changedOutput schema / (root)

Previous value: -{
-  "properties": {
-    "clause_note": {
-      "type": "string"
-    },
-    "decision": {
-      "properties": {
-        "execution_state": {
-          "type": "string"
-        },
-        "reason": {
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "determinations": {
-      "items": {
-        "properties": {
-          "claimed_charge_minor": {
-            "type": "integer"
-          },
-          "days_failed": {
-            "type": "integer"
-          },
-          "delta_minor": {
-            "type": "integer"
-          },
-          "fail_id": {
-            "type": "string"
-          },
-          "par_amount_minor": {
-            "type": "integer"
-          },
-          "rate_diff_bps": {
-            "type": "integer"
-          },
-          "recomputed_charge_minor": {
-            "type": "integer"
-          },
-          "reference_rate_bps": {
-            "type": "integer"
-          },
-          "verdict": {
-            "type": "string"
-          }
-        },
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "diff_tolerance_minor": {
-      "type": "integer"
-    },
-    "fail_count": {
-      "type": "integer"
-    },
-    "rejected_inputs": {
-      "type": "array"
-    },
-    "scope_note": {
-      "type": "string"
-    },
-    "total_claimed_charge_minor": {
-      "type": "integer"
-    },
-    "total_recomputed_charge_minor": {
-      "type": "integer"
-    },
-    "verdict": {
-      "type": "string"
-    }
-  },
-  "type": "object"
-}New value: +null

Changed1 schema field changedSep 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "clause_note": {
+      "type": "string"
+    },
+    "decision": {
+      "properties": {
+        "execution_state": {
+          "type": "string"
+        },
+        "reason": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "determinations": {
+      "items": {
+        "properties": {
+          "claimed_charge_minor": {
+            "type": "integer"
+          },
+          "days_failed": {
+            "type": "integer"
+          },
+          "delta_minor": {
+            "type": "integer"
+          },
+          "fail_id": {
+            "type": "string"
+          },
+          "par_amount_minor": {
+            "type": "integer"
+          },
+          "rate_diff_bps": {
+            "type": "integer"
+          },
+          "recomputed_charge_minor": {
+            "type": "integer"
+          },
+          "reference_rate_bps": {
+            "type": "integer"
+          },
+          "verdict": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "diff_tolerance_minor": {
+      "type": "integer"
+    },
+    "fail_count": {
+      "type": "integer"
+    },
+    "rejected_inputs": {
+      "type": "array"
+    },
+    "scope_note": {
+      "type": "string"
+    },
+    "total_claimed_charge_minor": {
+      "type": "integer"
+    },
+    "total_recomputed_charge_minor": {
+      "type": "integer"
+    },
+    "verdict": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedAug 7, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive, and the description adds real context on top: transient processing with no storage or logging, a client-side vs server-side execution split that can return a browser delegation URL, and an AP2 artifact export carrying execution_hash for provenance. It also clarifies that the FV-status link is a snapshot rather than a subscription. Minor weakness: compute-mode text largely restates the schema enum.

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?

Leads with low-value boilerplate ('OpenChainGraph compute node (compliance_control)'), repeats the compute-mode behavior already in the schema, embeds a long FV-status hash URL, and cuts the core formula off mid-sentence ('per the published trading practice (2016 re...'). The useful content is buried rather than front-loaded.

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 annotations covering the safety profile and no output schema, the description still enumerates all ten return fields and points to describe_tool for the schema, plus privacy and execution-mode details. The clipped formula and undocumented nested 'fails' entry structure keep it from being fully self-sufficient.

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?

Overall schema description coverage is 100%, so the baseline is 3. The description does add some meaning for the otherwise bare nested policy_parameters (reference rate, par amount, days failed feeding the formula), but it does not explain how the cutoff date, per-fail rejections, or diff_tolerance_minor behave.

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 (recompute) and a very specific resource (TMPG fails-charge on UST/agency/agency-MBS settlement fails) and even states the exact formula (max(0, 3% minus reference rate) / 360 x par x days). The domain specificity distinguishes it from the many other recompute_* siblings, though it never explicitly contrasts with any of them.

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?

Gives a clear call scenario: recomputing a fails-charge claim that a buyer presents to a failing seller in a settlement fail. It does not name alternatives or state when not to use it, and the compute-mode paragraph is configuration guidance rather than usage routing.

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.

TMPG Fails-Charge Recompute

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources