AINumbers Fintech Intelligence Suite

Sanctions Screening-Program Quality Scorer

score_sanctions_screening_quality

Read-onlyIdempotent

Sanctions Screening-Program Quality Scorer: OpenChainGraph compute node (model_governance). 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-92-screening-list-coverage-checker, art-93-fuzzy-match-calibration-scorer. Output feeds: cry-05-agent-action-audit-trail-aggregator. Open at: https://ainumbers.co/chaingraph/art-97-sanctions-screening-quality-scorer.html FV-status (published/proven/still-trusted for this spec): /fv-status/dfdd7083d50dfec46270d5ca2c4a06852efd98bdc1ae8d20e3d3b191e9b14ac7.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched.

Input Schema

TableJSON 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". See the tool's manifest for field names.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`note`	No
`composite_pct`	No
`program_grade`	No
`wolfsberg_note`	No
`component_scores`	No
`component_weights`	No
`reference_version`	No
`improvement_priorities`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "component_scores": {
+      "properties": {
+        "alert_tuning": {
+          "type": "integer"
+        },
+        "escalation_workflow": {
+          "type": "integer"
+        },
+        "list_coverage": {
+          "type": "integer"
+        },
+        "match_calibration": {
+          "type": "integer"
+        },
+        "model_validation": {
+          "type": "integer"
+        }
+      },
+      "type": "object"
+    },
+    "component_weights": {
+      "properties": {
+        "alert_tuning": {
+          "type": "integer"
+        },
+        "escalation_workflow": {
+          "type": "integer"
+        },
+        "list_coverage": {
+          "type": "integer"
+        },
+        "match_calibration": {
+          "type": "integer"
+        },
+        "model_validation": {
+          "type": "integer"
+        }
+      },
+      "type": "object"
+    },
+    "composite_pct": {
+      "type": "integer"
+    },
+    "improvement_priorities": {
+      "items": {
+        "properties": {
+          "action": {
+            "type": "string"
+          },
+          "current_score": {
+            "type": "integer"
+          },
+          "dimension": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "note": {
+      "type": "string"
+    },
+    "program_grade": {
+      "type": "string"
+    },
+    "reference_version": {
+      "type": "string"
+    },
+    "wolfsberg_note": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedJun 22, 2026

TDQS

C2.9/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description adds real behavior beyond them: deterministic execution, transient processing with no storage or logging, a synthetic/anonymised-input-only constraint, EVM-style browser delegation for gpu:true nodes, and an execution_hash AP2 export for provenance. These are concretely useful constraints an agent must honor.

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?

Structure is poor: the front-loaded sentence is a title restatement, the middle is repeated boilerplate ('Deterministic OpenChainGraph compute node'), and the trailing FV-status URL plus raw 64-hex receipt hash is noise an agent cannot act on. Little of the text earns its place before the actual purpose is clear.

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?

An output schema exists, so return-value explanation is not owed, and chaining/provenance/privacy are covered. However the description never fills the real gap: policy_parameters is untyped and deferred to an external manifest ('See the tool's manifest for field names'), so the agent still doesn't know what decision inputs to supply or what the score means.

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 compute/parent_hashes/parent_tool_ids/policy_parameters are already documented in the schema and the baseline is 3. The description's compute-mode text largely echoes the schema's own compute description and adds no field-level syntax or format detail.

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 ('Sanctions Screening-Program Quality Scorer: OpenChainGraph compute node') rather than describing the operation, and the body is dominated by compute-infrastructure boilerplate. It does add useful scope via the upstream artifacts it consumes (list-coverage-checker, fuzzy-match-calibration-scorer), implying it aggregates those into a quality score, but it never states what 'screening-program quality' comprises or what is actually computed.

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 guidance and no routing to the many adjacent siblings (run_sanctions_screening_fit, check_screening_list_coverage, score_fuzzy_match_calibration, build_sanctions_screening_evidence_pack). The artifact chain ('consumes from…', 'output feeds…') hints at pipeline position but leaves selection entirely to inference.

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.