Skip to main content
Glama

DPX — Institutional Cross-Border Settlement

computer_use.pay

Destructive

Complete a payment that Claude's computer use session has identified on screen — a checkout form, wire transfer UI, invoice approval, or vendor portal payment step. Call this instead of typing credentials into a UI. Describe what you see on screen, provide the amount and recipient, and DPX runs the full oracle gate → compliance screen → settlement flow. Returns a receipt. Use whenever computer use encounters a payment that would otherwise require human re-entry or approval.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
amountYesPayment amount in USD as shown on screen
purposeYesPayment purpose — e.g. vendor-invoice, contractor-payment, subscription, procurement
sandboxNoSet false for live execution. Default: true
screen_contextYesDescribe what is visible on screen — the payment form, vendor name, invoice number, or UI context. Used for audit trail.
counterparty_nameNoVendor or payee name as shown on screen
recipient_addressYesRecipient wallet address (0x...). If only bank/email visible, use settlement.nl instead.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
feeUsdNo
netUsdNo
reasonNo
statusNo
txHashNo
decisionNo
aiDecisionNo
aiConfidenceNo
settlementIdNo

Schema Changelog

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

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnly=false. The description adds meaningful context beyond annotations: 'DPX runs the full oracle gate → compliance screen → settlement flow' and 'Returns a receipt,' clarifying that this triggers a multi-step pipeline, not just a simple payment call. No contradiction with annotations.

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?

Three sentences with a front-loaded purpose and examples, followed by usage alternatives and execution flow. Efficient and well-structured, though there is slight redundancy between 'Call this instead of typing credentials into a UI' and 'Use whenever computer use encounters a payment...'

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?

Given the tool's complexity, the rich input/output schemas, and a large sibling set, the description is quite complete: it covers the execution pipeline, return receipt, and the key distinction from manual credential entry. A short note on prerequisites or authorization would elevate it, but the current coverage is solid.

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 baseline applies. The main description mentions 'provide the amount and recipient' and 'Describe what you see on screen,' but these add little beyond the already-rich parameter descriptions in the schema. The useful alternative-tool hint for recipient_address is in the schema, not the main description.

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?

Specific verb 'Complete a payment' with clear context: identified on screen by computer use, with concrete examples (checkout form, wire transfer UI, invoice approval, vendor portal). Distinguishes from siblings by 'Call this instead of typing credentials into a UI,' making the tool's unique role explicit.

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

Usage Guidelines5/5

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

Explicit when-to-use guidance: 'Use whenever computer use encounters a payment that would otherwise require human re-entry or approval.' Also provides an alternative: 'If only bank/email visible, use settlement.nl instead' (in schema), and tells agents to call this instead of typing credentials into a UI.

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.

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.