Skip to main content
Glama

BRAINIAC Accounts Payable

Match an invoice to a purchase order

accounts-payable_purchase-order-match

Match the invoice to a purchase order supplied in the request. Purchase orders are not looked up or created. Lines match on SKU when both sides have one, otherwise on the same description. Price $0.06 USDC. POST /api/v1/accounts-payable/purchase-order-match. Unpaid calls return 402 and do not run.

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": "accounts-payable_purchase-order-match"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
invoiceNo
purchaseOrderNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

With no annotations present, the description carries the full burden and does substantial work: it discloses the matching precedence rule (SKU first, description fallback), the price ($0.06 USDC), the transport (POST path), and the failure mode (402 on unpaid calls, which do not execute). It stops short of stating whether the call is idempotent or what the successful response contains.

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?

Five short sentences, front-loaded with the operation and scope, then matching logic, then cost and failure behavior. No filler and no repetition of the title.

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

Completeness3/5

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

Given nested objects, no annotations, no output schema, and a paid endpoint, the description covers cost and failure behavior well but leaves two material gaps: the relationship between `file` and `invoice`, and the shape of a successful match result. An agent could invoke it but might supply the wrong input combination on the first attempt.

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

Parameters2/5

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

Schema description coverage is 0% across three deeply nested top-level objects, so the description must compensate and largely does not. It explains how line items are compared (SKU, then description), which is genuinely useful, but the `file` parameter — accepting PDF/plain text/CSV — is never mentioned, leaving the agent unable to tell whether it is an alternative to the `invoice` object or an additional input, and no top-level parameter is marked required.

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?

States a specific verb and resource ('Match the invoice to a purchase order') and immediately bounds the scope with 'Purchase orders are not looked up or created', which separates it from any sibling that fetches or creates PO data. An agent can identify the operation without opening the schema.

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 negative guidance ('Purchase orders are not looked up or created') tells the agent the PO must already be in hand, which is the key precondition. It does not name a specific alternative tool for cases where a PO needs to be retrieved first, but no sibling in the provided set performs matching, so the routing risk is low.

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