Skip to main content
Glama

AINumbers Fintech Intelligence Suite

by co.ainumbers
OverviewDiscussionsAdmin

AI-Tool-Usage Workpaper Record

build_ai_workpaper_record
Read-onlyIdempotent

AI-Tool-Usage Workpaper Record: OpenChainGraph compute node (compliance_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. Open at: https://ainumbers.co/chaingraph/art-380-build-ai-workpaper-record.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("build_ai_workpaper_record").

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": {
-    "checks": {
-      "items": {
-        "properties": {
-          "check": {
-            "type": "string"
-          },
-          "detail": {
-            "type": "string"
-          },
-          "pass": {
-            "type": "boolean"
-          }
-        },
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "disclaimer": {
-      "type": "string"
-    },
-    "documentation_standard_ref": {
-      "type": "string"
-    },
-    "engagement": {
-      "properties": {
-        "engagement_id": {
-          "type": "string"
-        },
-        "reporting_period": {
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "evidence_binding": {
-      "properties": {
-        "execution_hash": {
-          "type": "string"
-        },
-        "generated_at": {
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "limitations": {
-      "properties": {
-        "declared_conventions": {
-          "type": "string"
-        },
-        "determinism_class": {
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "previous_workpaper_hash": {
-      "type": "string"
-    },
-    "sign_off": {
-      "properties": {
-        "reviewer_role": {
-          "type": "string"
-        },
-        "reviewer_statement": {
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "tool_identity": {
-      "properties": {
-        "kernel_digest": {
-          "type": "string"
-        },
-        "tool_id": {
-          "type": "string"
-        },
-        "tool_version": {
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "zero_pii_notice": {
-      "type": "string"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "checks": {
+      "items": {
+        "properties": {
+          "check": {
+            "type": "string"
+          },
+          "detail": {
+            "type": "string"
+          },
+          "pass": {
+            "type": "boolean"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "disclaimer": {
+      "type": "string"
+    },
+    "documentation_standard_ref": {
+      "type": "string"
+    },
+    "engagement": {
+      "properties": {
+        "engagement_id": {
+          "type": "string"
+        },
+        "reporting_period": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "evidence_binding": {
+      "properties": {
+        "execution_hash": {
+          "type": "string"
+        },
+        "generated_at": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "limitations": {
+      "properties": {
+        "declared_conventions": {
+          "type": "string"
+        },
+        "determinism_class": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "previous_workpaper_hash": {
+      "type": "string"
+    },
+    "sign_off": {
+      "properties": {
+        "reviewer_role": {
+          "type": "string"
+        },
+        "reviewer_statement": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "tool_identity": {
+      "properties": {
+        "kernel_digest": {
+          "type": "string"
+        },
+        "tool_id": {
+          "type": "string"
+        },
+        "tool_version": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "zero_pii_notice": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  3. Added

TDQS

C2.9/5.0
Behavior4/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses substantive behavior: inputs are processed transiently and not stored/logged/retained, gpu:true nodes always delegate to the browser, compute:'browser' returns a delegation URL, and the output is a chained AP2 artifact carrying execution_hash. It also explains the offline FV-status receipt semantics. These are real behavioral facts an agent could not get from the structured fields.

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 a single dense block mixing purpose, compute semantics, privacy notes, artifact format, a full URL and a 64-character hash string. The URL and hash digest are selection-irrelevant clutter, and the closing 'call describe_tool(...)' line is confusing given no output schema exists. Front-loading is partial but the whole is bloated.

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?

For a nested-object tool with no output schema, the description covers execution modes, data handling, chaining inputs and the exported artifact, which is reasonable. But it defers the actual decision-function field names to an external manifest and never explains what the produced workpaper record contains, leaving a substantive gap for a 4-parameter nested tool.

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 schema already documents compute, parent_hashes, parent_tool_ids and policy_parameters, and the description's compute-mode text largely restates it. It adds only the chaining intent (parent hashes from upstream artifacts) at the level the schema already conveys. Baseline 3 is appropriate.

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 name and opening line identify a specific artifact (an AI-tool-usage workpaper record) and its container (an OpenChainGraph compliance_mandate compute node) that exports an AP2 artifact with an execution_hash. However, the description never says what a workpaper record actually contains or why one builds it, and it does not distinguish this tool from near-identical siblings such as build_ai_decision_log_record or build_ai_training_data_lineage_record. Purpose is inferable but buried under platform jargon.

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 one operational constraint ('Use synthetic or anonymised inputs only') but no statement of when to choose this tool over the many sibling record-builder tools, nor any prerequisite or exclusion. The compute-mode explanation describes how execution happens, not when this tool is the right one.

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