Skip to main content
Glama

BRAINIAC Accounts Payable

Review an invoice for payment

accounts-payable_review

Combine the invoice checks into one review. No payment is initiated, and a clear review is not an approval to pay. Price $0.12 USDC. POST /api/v1/accounts-payable/review. 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_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
invoiceNo
candidatesNo
purchaseOrderNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.3/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does disclose several non-obvious traits: no payment is initiated, a clean review is explicitly not an approval to pay, the call costs $0.12 USDC, and unpaid calls fail with HTTP 402 without executing. That is a solid disclosure of side-effect boundaries and a paid-endpoint precondition. It does not say which checks are performed, whether the operation is read-only against the supplied data, or what the review 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.

Conciseness4/5

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

Four short, front-loaded sentences with no filler: what it does, what it does not do, cost, endpoint, failure mode. The only near-redundancy is the pair 'no payment is initiated' and 'a clear review is not an approval to pay', though the second adds the distinct point that a passing review is not authorization.

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

Completeness2/5

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

This is a high-complexity tool — four nested object inputs, no annotations, no output schema — and the description covers only commercial and failure semantics. An agent still cannot tell which inputs to send for a given review or what the review returns, which is the core information needed to invoke it correctly.

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?

Four top-level parameters (file, invoice, candidates, purchaseOrder) with 0% schema description coverage and deep nesting, yet the description says nothing about any of them — not what 'candidates' means, not when to supply a parsed invoice versus a file, not how purchaseOrder drives matching. The schema enforces shapes and bounds but conveys no intent, so this is a real gap the description should have filled.

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?

Specific verb ('review') and resource (invoice), and it explains that this is the composite of the individual invoice checks, which implicitly distinguishes it from the single-check siblings (anomaly-detect, duplicate-detect, tax-validate, total-validate, po-match). It does not name any sibling explicitly, so an agent must infer the routing from the sibling names alone.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: 'Combine the invoice checks into one review' tells the agent this is the batch/aggregate option, and the two negative clauses rule out using it to pay. There is no explicit 'use this when you want all checks; use X when you want only one check' rule, and no prerequisites about which inputs are needed for which checks to run.

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