Skip to main content
Glama

AINumbers Fintech Intelligence Suite

by co.ainumbers

Agent On-Behalf-Of (OBO) Mandate Validator

validate_agent_obo_mandate
Read-onlyIdempotent

Agent On-Behalf-Of (OBO) Mandate Validator: 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. Consumes upstream artifacts from: art-150-mcp-tool-scope-revocation-auditor. Output feeds: art-152-mcp-task-lifecycle-validator. Open at: https://ainumbers.co/chaingraph/art-151-agent-obo-mandate-validator.html FV-status (published/proven/still-trusted for this spec): /fv-status/e5ebd9cab6d424d5a202b2144bf9dacc14abf4ed24f3f0ac3adbecdd87c14872.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched.

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.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
gapsNo
verdictNo
has_scopeNo
has_intentNo
has_subjectNo
not_expiredNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "gaps": {
+      "type": "array"
+    },
+    "has_intent": {
+      "type": "boolean"
+    },
+    "has_scope": {
+      "type": "boolean"
+    },
+    "has_subject": {
+      "type": "boolean"
+    },
+    "not_expired": {
+      "type": "boolean"
+    },
+    "verdict": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  2. Added

TDQS

B3.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description goes well beyond this: it discloses deterministic execution, that inputs are 'processed transiently... not stored, logged, or retained,' that browser mode 'returns a browser delegation URL instead' of a result, and that an 'AP2 artifact with execution_hash for chain provenance' is exported. None of this contradicts the annotations — determinism and transient processing align with the idempotent/read-only hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and mostly purposeful — compute modes, transient processing, and chain provenance each earn their place. But 'Deterministic OpenChainGraph compute node' repeats 'OpenChainGraph compute node' from the immediately preceding sentence, and the FV-status tail (receipt hash, offline verification semantics, 'a snapshot, not a subscription') is trust metadata that goes beyond what an agent needs to 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?

Operationally the description is strong: compute behavior, data-handling policy, chain provenance, and verification all covered, and an output schema exists so return values need no explanation. The gaps are domain-level: what an OBO mandate is, what the 'decision function' in policy_parameters actually evaluates, and what an agent should do when a browser delegation URL is returned instead of a result. For an agent choosing among scores of validate_* siblings, that missing semantic core matters.

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 coverage is 100%, so the schema already documents all four parameters, including a thorough explanation of the compute enum (auto/server/browser defaults and gpu:true delegation). The description's compute-mode prose mostly restates the schema, adding only minor detail like 'Cloudflare Workers' as the server-side location. It adds nothing material about parent_hashes, parent_tool_ids, or policy_parameters beyond the schema, so the baseline 3 applies.

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 resource (Agent OBO Mandate) and operation (validate) and adds that it is a compliance_mandate compute node, so it is not a pure tautology. However, it never states what 'validating an OBO mandate' actually checks or decides, and the prose is dominated by compute-infrastructure details (gpu nodes, Cloudflare Workers, browser delegation) rather than validation semantics. Sibling tools like validate_ap2_mandate_chain and validate_ap2_mandate_credential are not differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied through the chain position ('Consumes upstream artifacts from: art-150-mcp-tool-scope-revocation-auditor. Output feeds: art-152-mcp-task-lifecycle-validator') and the 'Use synthetic or anonymised inputs only' constraint, which tells an agent when input data is permissible. But the description never explicitly states when to choose this tool over the many sibling mandate validators, nor does it list prerequisites for invocation.

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
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.9/5.0
Disambiguation1/5

With 698 tools covering overlapping regulatory and compliance domains, many tools have near-identical names and purposes (e.g., check_genius_reserve_disclosure vs check_genius_reserve_disclosure_conformance, multiple DORA incident classifiers, several AP2 mandate validators). The highly templated descriptions further reduce distinctiveness, making reliable tool selection by an agent effectively impossible.

Naming Consistency4/5

The overwhelming majority of tools follow a consistent snake_case verb_noun pattern (assess_*, build_*, compute_*, validate_*, verify_*). Minor deviations exist (camt053_parse, workbook_evaluate, ha_gate_status, sdjwt_issue, etc.), but they are a small fraction of the total and follow recognizable domain-prefix conventions.

Tool Count1/5

698 tools is an extreme oversizing for any server, far beyond the 50+ threshold for a low score. Even with dedicated search/discovery tools, this unwieldy surface guarantees cognitive overload, high misselection risk, and severe practical usability problems.

Completeness4/5

The suite covers an extraordinarily broad range of fintech/regulatory domains — capital adequacy, AML, payments, crypto, AI governance, trade finance, and many verification/recompute lifecycles. Obvious gaps are difficult to identify, though the set is not a coherent single lifecycle and some niche areas are inevitably absent.

Resources