Skip to main content
Glama

AINumbers Fintech Intelligence Suite

by co.ainumbers
OverviewDiscussionsAdmin

Work Mandate Compiler

compile_work_mandate
Read-onlyIdempotent

Work Mandate Compiler: OpenChainGraph compute node (governance_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-274-compile-work-mandate.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("compile_work_mandate").

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": {
-    "chain_config": {
-      "properties": {
-        "steps": {
-          "items": {
-            "properties": {
-              "gate": {
-                "properties": {
-                  "default": {
-                    "type": "string"
-                  },
-                  "input": {
-                    "type": "string"
-                  },
-                  "rules": {
-                    "items": {
-                      "properties": {
-                        "next": {
-                          "type": "string"
-                        },
-                        "op": {
-                          "type": "string"
-                        },
-                        "value": {
-                          "type": "boolean"
-                        }
-                      },
-                      "type": "object"
-                    },
-                    "type": "array"
-                  }
-                },
-                "type": "object"
-              },
-              "id": {
-                "type": "string"
-              },
-              "tool_id": {
-                "type": "string"
-              }
-            },
-            "type": "object"
-          },
-          "type": "array"
-        }
-      },
-      "type": "object"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "chain_config": {
+      "properties": {
+        "steps": {
+          "items": {
+            "properties": {
+              "gate": {
+                "properties": {
+                  "default": {
+                    "type": "string"
+                  },
+                  "input": {
+                    "type": "string"
+                  },
+                  "rules": {
+                    "items": {
+                      "properties": {
+                        "next": {
+                          "type": "string"
+                        },
+                        "op": {
+                          "type": "string"
+                        },
+                        "value": {
+                          "type": "boolean"
+                        }
+                      },
+                      "type": "object"
+                    },
+                    "type": "array"
+                  }
+                },
+                "type": "object"
+              },
+              "id": {
+                "type": "string"
+              },
+              "tool_id": {
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}
  3. Added

TDQS

C2.9/5.0
Behavior4/5

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

The description goes well beyond the annotations by disclosing transient processing ('not stored, logged, or retained'), the server-vs-browser delegation behavior, deterministic execution, and the exported AP2 artifact with execution_hash for provenance. With readOnly/idempotent hints already covering safety, this adds real operational context an agent would not otherwise have.

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 identity is front-loaded, but the body is bloated with a full URL, a 64-character FV-status hash, an explanation of receipt-offline verification, and a 'call describe_tool(...)' pointer. These consume a large share of the description without helping the agent select or invoke the tool correctly.

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 four-parameter, zero-required tool with a nested open-ended policy_parameters object and no output schema, the description covers execution modes and data handling but leaves the actual decision-function fields to an external manifest and the return shape to describe_tool. It is minimally adequate rather than complete.

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. The description restates the compute-mode semantics (already in the schema) and defers policy_parameters field names to 'the tool's manifest', adding no new parameter meaning. Baseline 3 is correct.

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 description identifies the tool as a 'deterministic OpenChainGraph compute node (governance_mandate)' that 'exports an AP2 artifact with execution_hash', so the resource and category are clear. However, it never states plainly what a 'work mandate' is or what 'compile' produces, and given the many mandate siblings (ap2_aml_mandate_builder, build_google_ap2_mandate, draft_ap2_mandate_credential) it offers no differentiation among them.

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 when-to-use or when-not-to-use guidance relative to the mandate siblings. The compute-mode discussion ('auto'/'browser') is a mode selection, not a routing rule, and 'Use synthetic or anonymised inputs only' is a data constraint rather than usage guidance. An agent is left to infer when this tool is the right call.

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