Skip to main content
Glama

DPX — Institutional Cross-Border Settlement

by io.github.untitledfinancial

settlement.execute

Destructive

Execute a DPX cross-border settlement. The Settlement Agent checks oracle conditions, reasons with Claude AI, and executes on-chain (or returns sandbox result if sandbox=true). Returns settlement ID, status (executed/held/sandbox/failed), tx hash, net amount, fees, oracle conditions, and AI reasoning. Default: sandbox=true — set sandbox=false only for live execution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
amountYesAmount in source currency units
purposeNoPayment purpose: intercompany, vendor-payment, payroll, treasury
quoteIdNoPre-fetched quoteId from get_quote (optional — agent fetches live if omitted)
sandboxNoSandbox mode — real calculations, no on-chain execution. Default: true.
esgScoreNoESG score override 0–100 (testing only)
referenceIdNoExternal reference ID (invoice number, TMS ID, etc.)
sourceCurrencyYesSource currency: USD, EUR, GBP, USDC, EURC
recipientAddressYesOn-chain recipient wallet address (0x...)
destinationCurrencyYesDestination currency: USD, EUR, GBP, USDC, EURC

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultNo
summaryNoHuman-readable settlement outcome summary
httpStatusNoHTTP status from Settlement Agent

Schema Changelog

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

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations include destructiveHint=true (mutation) and readOnlyHint=false. The description goes beyond by explaining the agent's internal behavior (checks oracle conditions, reasons with Claude AI) and the sandbox fallback. It doesn't detail irreversibility or failure reasons, but it provides valuable context consistent with annotations. No contradiction.

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

Conciseness5/5

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

Three sentences cover purpose, behavior, return values, and safe usage. Every sentence is information-dense with no filler. The sandbox warning is front-loaded for safety-critical usage.

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

Completeness4/5

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

For a complex 9-parameter tool with an output schema, the description effectively covers the execution flow, sandbox mode, and live execution constraint. It could mention prerequisites (e.g., need for a quote) more explicitly, but quoteId is described as optional. Overall, sufficiently complete for an agent to invoke correctly.

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% with all parameters described. The description adds the sandbox/live distinction and return value list, but does not significantly enhance individual parameter understanding. Baseline of 3 is appropriate since structured schema already handles parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action: 'Execute a DPX cross-border settlement' with explicit process details (checks oracle conditions, reasons with Claude AI, executes on-chain). It distinguishes from sibling tools like settlement.quote (quoting) and settlement.status (status check) by focusing on execution.

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

Usage Guidelines4/5

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

Provides explicit guidance on sandbox vs live execution: 'Default: sandbox=true — set sandbox=false only for live execution.' This is clear when-to-use context. However, it doesn't explicitly mention alternatives like batch_settle for batch scenarios, so it earns a 4 rather than 5.

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

All DPX — Institutional Cross-Border Settlement 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

A3.6/5.0
Disambiguation2/5

Many tools have overlapping purposes, such as multiple stablecoin routing options (route vs stability.stablecoin_route), several compliance pre-checks (flow_check, policy.check, mercury.ach_authorize), and numerous FX/stability tools (oracle.stability, stability.corridor, market.fx, fx.rate). Even with detailed descriptions, the boundaries are subtle and an agent could easily select the wrong tool.

Naming Consistency3/5

The dot-separated namespace convention is mostly consistent and readable, but verb vs noun usage varies (e.g., settlement.execute vs batch_settle vs route). Subscription tools also mix forms (intelligence.subscribe vs intelligence.subscription.get/delete), showing minor inconsistency.

Tool Count1/5

81 tools is an extreme count for a settlement server. Even accounting for the broad 'institutional' scope, the volume overwhelms the core purpose and creates a heavy cognitive load for agents, far beyond the typical 3-15 well-scoped tool set.

Completeness3/5

The core settlement lifecycle is well-covered (quote, execute, track, receipt, batch), but there are notable gaps such as missing policy update/delete and no receipt retrieval (only create). While many tangential domains are over-covered, certain CRUD operations are absent, creating dead ends.

Resources