Skip to main content
Glama

AICTIONBOT™ Werkbank

Account helper: suggested general ledger account under SKR03 or SKR04 for each invoice line, with uncertain lines marked

suggest_accounts
Read-onlyIdempotent

Takes invoice lines (text, amount, supplier) and the chart (SKR03 or SKR04, German standard charts of accounts) and suggests a general ledger account per line from the category of the line, with notes for capitalisation (hardware over 800 euros net, machinery), incidental purchase costs for freight, and travel. Lines with one keyword hit or a special case are marked uncertain; lines without a match have no suggestion. Returns the suggestion per line and the total per account. A suggestion, not tax advice; the business's own chart and tax advisor take priority. Licence, or one free check every 30 days.

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": {
      "lines": "<lines>"
    },
    "name": "suggest_accounts"
  }
}

Input Schema

NameRequiredDescriptionDefault
chartNoChart of accounts. Default SKR03.
linesYesInvoice lines: text, amount (net), supplier. German column names work too.
languageNoLanguage of the answer. Default de.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, yet the description still adds real behaviour: single-keyword matches and special cases are flagged uncertain, unmatched lines return no suggestion, capitalisation and freight/travel rules trigger notes, and there is a licence/free-check limit of one per 30 days. That rate-limit and partial-result disclosure is exactly the kind of context annotations cannot carry.

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?

Front-loaded with the verb and inputs, and the trailing sentences on edge cases, disclaimer and licensing each carry information. It is a dense single paragraph with some run-on construction, which costs a little readability but not content.

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

Completeness5/5

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

For a read-only suggestion tool with no output schema, the description covers inputs, per-line and aggregate return shape, uncertainty marking, no-match behaviour, domain rules, a disclaimer and rate limits. An agent has everything needed to call it and to interpret what it gets back.

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% and the schema already documents chart, lines and language, so the baseline of 3 applies. The description adds domain meaning only indirectly (amount is net, which matters for the 800-euro capitalisation threshold, and German column names work), not per-parameter semantics beyond what the schema states.

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?

Names a concrete verb and resource ('suggests a general ledger account per line') plus the exact scope (SKR03/SKR04, per invoice line). It is specific enough that an agent knows what comes back (suggestion per line, totals per account), but it never contrasts itself with sibling tools such as check_invoice or check_einvoice, so sibling differentiation is left implicit.

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 context is implied rather than stated: it tells you the inputs (invoice lines plus chart) and the output, from which an agent can infer when to reach for it. There is no explicit when-to-use/when-not guidance and no named alternative for closely related invoice-checking tools.

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.