Skip to main content
Glama

Nityaflow GST credit match

Check an AI agent's payment against the mandate and the instruction

agent_payment_check
Read-onlyIdempotent

When the user asks for a payment check, checks a proposed AI-agent payment against the person's mandate (who allowed it, limits per payment and per period, allowed shops and UPI IDs, end date) and against what the person actually asked for (items, quantities, budget, shop). It works the total out again from the cart lines, and flags lookalike payees, extra items, too much quantity, going over a limit and repeat payments. Returns every check and a receipt signed by Nityaflow. It never pays, holds or moves money: a licensed bank or payment app does that, only after a person approves.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "mandate": "<mandate>",
      "intent": "<intent>",
      "action": "<action>"
    },
    "name": "agent_payment_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesThe payment the agent proposes: {merchant, vpa, lines: [{name, qty, unit, price}], fees, total}.
intentYesWhat the person asked for: {text, items: [{name, qty, unit}], budget, merchant}. Units: kg, g, l, ml, pc, pack, dozen.
historyNoEarlier payments under this mandate: [{at, total, vpa, status: paid}]. Used for the period limit and repeat check.
mandateYesThe permission: {authorised_by, purpose, per_payment, per_period, period (day, week, month or 90 days), merchants: [{name, vpa, category}], approve_above, valid_from, valid_to}.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

The annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, and the description is fully consistent with them while adding real substance: it recomputes the total from cart lines rather than trusting the submitted total, discloses the specific failure classes it flags (lookalike payees, extra items, excess quantity, limit breaches, repeat payments), and states what it returns (all checks plus a signed receipt). It also draws a hard boundary – it never pays, holds or moves money, and a licensed bank does that only after human approval – which is exactly the kind of authority/side-effect context annotations cannot express.

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 content is dense but every clause earns its place – the mandate facets, the intent facets, the flags, the return value, and the no-money-movement boundary are all load-bearing. The one structural weakness is that the trigger clause ('When the user asks for a payment check') is fused into the same sentence as the core action, so the definition of what the tool does arrives mid-sentence rather than being front-loaded.

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 four-parameter tool with nested objects and no output schema, the description carries the necessary load: it explains what is compared, what anomalies are reported, and that the response contains all checks plus a signed receipt. The remaining gap is the shape of the outcome – it does not say whether a failed check returns an error, a pass/fail verdict, or a structured list of findings, which matters for an agent deciding how to act on the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description goes beyond the schema in a way that changes how the agent builds the call: it says the total is worked out again from the cart lines, telling the caller that action.lines matter more than action.total, and it spells out the mandate facets that will be tested (per-payment and per-period limits, allowed shops and UPI IDs, end date) so the caller knows which fields must be populated. It also names 'repeat payments' as a check, which implicitly explains why history must be supplied. That is genuine semantic lift over the parameter docs.

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

Purpose4/5

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

The description gives a specific verb and resource: it checks a proposed AI-agent payment against a mandate and against the person's stated intent, and enumerates exactly what is compared (limits, shops, UPI IDs, items, quantities, budget) plus the anomalies it flags. That is far more than a restatement of the name. It stops short of 5 because it never differentiates itself from the siblings verify_receipt and gst_credit_match, and a 'verify_receipt' tool is close enough that an agent could hesitate between them.

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?

The opening clause supplies a concrete trigger: 'When the user asks for a payment check,' which tells the agent when to reach for this tool. It also implies the preconditions – a mandate, a stated intent, and a proposed action must all exist before calling. It gives no explicit when-not guidance and names no alternative tool for the cases this one does not cover, so it sits at clear-context-without-exclusions rather than full 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.

Resources