Skip to main content
Glama
ap-agent MCP server

ap-agent MCP server

by Icandi40

check_invoice

Read-only

Extract invoice fields from pasted text or an inbox file and run a three-way match against the purchase order and receiving log to verify invoices without writing to the ledger.

Instructions

Extract fields from an invoice (pasted text, or a file in the inbox) and run the three-way match against the PO and receiving log. Writes nothing to the ledger.

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": "check_invoice"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNo
filenameNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with 'Writes nothing to the ledger' while adding real substance: that it extracts fields and performs a three-way match against PO and receiving log. It still omits what happens when the match fails or what the extracted fields are, but that is beyond the annotation bar.

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?

Two tightly written sentences with the action first and the safety constraint last. Every clause carries information; there is no boilerplate or repetition.

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 a read-only annotation, an output schema that covers return values, and only two optional parameters, this is close to complete. Minor missing context: where the inbox lives and how match failures surface, neither of which the output schema necessarily guarantees.

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

Parameters4/5

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

With 0% schema description coverage, the description has to carry the load, and it does map both parameters: 'text' is pasted invoice content and 'filename' is a file in the inbox. The gap is precedence — it does not say what happens if both are supplied or whether one is required over the other.

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?

States a specific verb-and-resource pair: extract invoice fields and run a three-way match against the PO and receiving log. An agent can picture the operation immediately. It does not name or contrast with the related write-path sibling (propose_bill), leaving that differentiation implicit rather than explicit.

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?

The parenthetical '(pasted text, or a file in the inbox)' gives concrete input contexts, and 'Writes nothing to the ledger' hints this is a pre-check rather than a booking step. However, there is no explicit statement of when to use this versus propose_bill or list_open_bills, and no prerequisites such as the PO needing to exist first.

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