Skip to main content
Glama

AINumbers Fintech Intelligence Suite

Money Primitives Demonstrator

money_primitives_demo
Read-onlyIdempotent

Money Primitives Demonstrator: 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/mcp.html FV-status (published/proven/still-trusted for this spec): /fv-status/565f2dd45a55e0ff0f8dafde8c1080f9e1484b32a5aaa96f4d7739a236b9258a.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched. Summary: Demonstrator node for the shared _money.bundle.mjs kernel: exact decimal parse at a caller-declared scale (closed grammar; exponent form, thousands separators and excess precision are named refusals), BigInt minor-unit arithmetic with no engine float on the value path, six named rounding modes in... Outputs: status, error_code, message, mode, mode_echo, ccy, exponent, places, currency_entry_echo, table_version, amount_echo, parsed_amount, rounded_amount, weights_echo, allocations, allocation_sum, truncate_excess_declared, closed_mode_set, bounds, float_sensitive, scope_note. Output schema: call describe_tool("money_primitives_demo").

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "money_primitives_demo"
  }
}

Input 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". Required: amount, ccy, mode, weights, currency_slice. Unknown keys are refused.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

C2.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description does add genuine context beyond that: transient processing with no storage/logging/retention, deterministic server-side execution on Cloudflare Workers, and an exported AP2 artifact carrying execution_hash for chain provenance. It still omits error behavior and what the browser delegation URL actually does when returned.

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

Conciseness4/5

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

The opening sentence pair is redundant ('OpenChainGraph compute node (compliance_control). Deterministic OpenChainGraph compute node.'), the FV-status URL and hash consume a large block, and the Summary is truncated mid-clause ('six named rounding modes in...'). The output field list is long but does carry information, and the front-loaded compute-mode paragraph is where an agent needs it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nested, four-parameter compute node with no output schema, the description leaves critical gaps: the Summary is cut off mid-sentence, the exact contract of policy_parameters currency_slice is undefined, and the reader is deferred to describe_tool('money_primitives_demo') for return values. The listed output field names are enumerated but never explained, so an agent cannot predict response semantics from this text alone.

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 pairing, and the policy_parameters keys including which are required and that unknown keys are refused. The description largely restates the compute-mode semantics already present in the schema and adds no new syntax, format, or ordering detail, 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 this as a 'Demonstrator node for the shared _money.bundle.mjs kernel' and the Summary names concrete operations (exact decimal parse at a declared scale, BigInt minor-unit arithmetic, six rounding modes, allocations). However, no single verb+resource framing is given and nothing distinguishes it from the many money-related siblings (e.g. allocate_ihb_interest, build_public_money_settlement_receipt), so the agent must infer that this is the generic rounding/allocation primitive.

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?

The compute modes (auto/server/browser) are explained thoroughly, but that is parameter behavior, not tool-selection guidance. There is no statement of when an agent should choose this demonstrator over sibling money tools, and the only usage constraint given is 'Use synthetic or anonymised inputs only,' which is a data-safety rule rather than routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.