Skip to main content
Glama

ARADIA | sovereign agentic systems

by com.aradia
OverviewDiscussionsAdmin

execute_procurement_order

[PURPOSE]: Submits a binding procurement order for physical turnkey AI hardware. Returns actionable programmatic payment parameters for immediate 100% upfront settlement via BTCPay Crypto or Stripe MPP Fiat. [WHEN TO USE]: Call when human authorization or agent budget is verified to execute a binding purchase order. [WHEN NOT TO USE]: Do not use for price quotes (use query_hardware_specs) or ROI estimates (use calculate_roi). Do not use to check order status (use track_order_status). [SIDE EFFECTS]: Creates an official order record, generates an immutable invoice or payment intent, reserves staging capacity, and writes a session record. Non-destructive.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
quantityNoNumber of appliance nodes to purchase (1-99).
po_numberNoOptional corporate purchase order number.
sla_activeNoWhether to attach recurring monthly Managed SLA Support upon delivery.
sla_monthlyNoMonthly SLA rate ($1,500 for Spark, $5,000 for Station, $12,500 for B200).
customer_nameNoName of the purchasing agent or executive.
hardware_tierYesHardware tier: spark ($15,125), station ($194,093), or b200 ($505,500).
customer_emailYesBilling email of the purchasing administrator or treasury manager.
payment_methodYesSettlement method: stripe_mpp (Fiat Shared Payment Token), btcpay_crypto (BTC/LN/USDT), stripe_fiat (Card), stripe_invoice (Wire invoice).
customer_companyNoDeploying company, firm, or entity name.
partner_ref_codeNoOptional 4-character referral code (e.g. 5FYVQ) to route 10% commission.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
amount_usdYes
invoice_idNo
payment_urlNo
payment_methodNo
payment_detailsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changed
    • changedInput schema / properties / customer_company / description
      Previous value: -"Company, DAO, or Organization name associated with this hardware deployment."New value: +"Deploying company, firm, or entity name."
    • changedInput schema / properties / customer_email / description
      Previous value: -"Email address of the purchasing administrator or target billing point."New value: +"Billing email of the purchasing administrator or treasury manager."
    • changedInput schema / properties / customer_name / description
      Previous value: -"Name of the AI Agent, Operator, or Administrator executing the order."New value: +"Name of the purchasing agent or executive."
    • changedInput schema / properties / hardware_tier / description
      Previous value: -"The hardware tier being purchased."New value: +"Hardware tier: spark ($15,125), station ($194,093), or b200 ($505,500)."
    • changedInput schema / properties / partner_ref_code / description
      Previous value: -"Optional 4-character referral code to route 10% commission to a registered partner."New value: +"Optional 4-character referral code (e.g. 5FYVQ) to route 10% commission."
    • changedInput schema / properties / payment_method / description
      Previous value: -"The preferred settlement method: (a) 'stripe_mpp' for fiat via Shared Payment Token (SPT), (b) 'btcpay_crypto' for raw on-chain BTC/LN/USDT JSON settlement, (c) 'btcpay_usdc_base' for USDC, (d) 'stripe_fiat' for Stripe Checkout URL, (e) 'stripe_invoice' for formal wire invoice."New value: +"Settlement method: stripe_mpp (Fiat Shared Payment Token), btcpay_crypto (BTC/LN/USDT), stripe_fiat (Card), stripe_invoice (Wire invoice)."
    • changedInput schema / properties / po_number / description
      Previous value: -"Optional purchase order number for reference."New value: +"Optional corporate purchase order number."
    • changedInput schema / properties / quantity / description
      Previous value: -"The number of appliance nodes to purchase."New value: +"Number of appliance nodes to purchase (1-99)."
    • changedInput schema / properties / sla_active / description
      Previous value: -"Whether SLA is active for this order."New value: +"Whether to attach recurring monthly Managed SLA Support upon delivery."
    • changedInput schema / properties / sla_monthly / description
      Previous value: -"Monthly SLA cost if active."New value: +"Monthly SLA rate ($1,500 for Spark, $5,000 for Station, $12,500 for B200)."
    • removedOutput schema / properties / amount_usd / description
      Removed value: -"Total purchase order amount in USD"
    • removedOutput schema / properties / invoice_id / description
      Removed value: -"Generated invoice or payment intent ID"
    • removedOutput schema / properties / payment_details / description
      Removed value: -"Raw destination addresses and amounts for crypto settlement"
    • removedOutput schema / properties / payment_method / description
      Removed value: -"Chosen payment rail"
    • removedOutput schema / properties / payment_url / description
      Removed value: -"Settlement URL"
    • addedOutput schema / required
      Added value: +[
+  "amount_usd"
+]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already include destructiveHint=false and readOnlyHint=false, but the description adds concrete side effects: creates an official order record, generates an immutable invoice/payment intent, reserves staging capacity, and writes a session record. It also explicitly states 'Non-destructive,' reinforcing and expanding the annotation context.

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?

The description is well-structured with labeled sections: PURPOSE, WHEN TO USE, WHEN NOT TO USE, and SIDE EFFECTS. Information is front-loaded and every sentence carries distinct value without filler.

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

Completeness5/5

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

For a 10-parameter mutating purchase tool, the description covers purpose, authorization prerequisites, exclusions, side effects, and the nature of the return. Since an output schema is present, detailed return-value documentation is not required here.

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%, with all properties documented including enums, defaults, and pricing. The description adds no additional parameter-level meaning, so the baseline 3 applies.

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 opens with a specific verb and resource: 'Submits a binding procurement order for physical turnkey AI hardware' and states that it returns payment parameters. The WHEN NOT TO USE section further distinguishes it from query_hardware_specs, calculate_roi, and track_order_status.

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 and WHEN NOT TO USE conditions are provided, including the required authorization context and three sibling alternatives to avoid. This gives an agent clear decision criteria with no ambiguity.

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

All ARADIA | sovereign agentic systems toolsInspect
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.

Resources