Skip to main content
Glama
ERP Procurement MCP Server

ERP Procurement MCP Server

Request human approval

request_approval
Idempotent

Route invoices that fail three-way matching to a person for approval; accept only received or on-hold invoices with exceptions and return the existing pending request instead of creating another.

Instructions

Sends an invoice that failed three-way matching to a person for approval. Only received or on-hold invoices with exceptions are accepted. Calling it again for the same invoice returns the pending request instead of creating a second one.

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": {
      "invoiceId": "<invoiceId>",
      "reason": "<reason>"
    },
    "name": "request_approval"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesWhy a person should look at this invoice, in plain language, for the approver
invoiceIdYesInternal invoice id, for example INV-1001
requestedByNoWho is asking, for the audit trailai-agent

Output Schema

NameRequiredDescriptionDefault
createdYes
approvalYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare idempotency and non-destructiveness, but the description adds concrete substance on top: the precondition that rejects ineligible invoices, and the exact duplicate-call behavior (return the pending request rather than creating a second one). It stops short of saying what the response contains on the acceptance path, but that is largely covered by the output schema.

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?

Three sentences, each carrying distinct information: what it does, who is eligible, and what happens on repeat invocation. The core action is front-loaded with no filler.

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 low-complexity, three-parameter mutation with a full output schema and four annotations, the description covers purpose, eligibility, and idempotent behavior adequately. The only minor omission is failure-mode behavior for ineligible invoices, which is partly inferable from the eligibility sentence.

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%, so all three parameters (invoiceId, reason, requestedBy) are already documented in the schema including format, length bounds, and audit-trail purpose. The description adds no parameter-level meaning beyond that, which is the expected baseline when the schema does the work.

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 gives a specific verb (sends) and resource (an invoice that failed three-way matching) plus the destination (a person for approval). This makes it trivially distinguishable from get_invoice, match_invoice, and search_invoices without opening any 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?

It states the eligibility gate clearly: only received or on-hold invoices with exceptions are accepted. It also gives the repeat-call condition (returns the pending request). What it lacks is an explicit pointer to what to do when the invoice is ineligible, but the when-to-use boundary is unambiguous.

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