Skip to main content
Glama

AICTIONBOT™ Werkbank

Expense checker: travel expense claims against the official German per diem, mileage and overnight rates, with double submissions, overlaps, missing receipts and weekends

check_expenses
Read-onlyIdempotent

AICTIONBOT™ expense checker by KULIC Advisory (tool 51). Takes a travel expense list (employee, start and end date, hours away for one-day trips, destination as country or city, km, vehicle, claimed meals, travel and hotel, receipt yes or no, meals provided such as "2 breakfasts") and checks every trip against the official rates as of 1 January 2026: meals in Germany 14 euros (more than 8 hours, arrival and departure day) and 28 euros (24 hours) under section 9 (4a) EStG, cut by 20 % per breakfast and 40 % per lunch or dinner provided; mileage 0.30 euros per km by car and 0.20 euros by other motor vehicles; overnight without receipt 20 euros in Germany; abroad the country and city rates of the German Federal Ministry of Finance letter of 5 December 2025 (all 214 entries built in, countries not listed use the Luxembourg rate). Also flags trips submitted twice, overlapping trips of the same person, missing receipts and weekend trips. Returns red and yellow findings per trip, claimed versus allowed per person and in total. Without a list, a destination returns its rates. Rates are fixed in the tool with source and date, nothing is fetched. Not tax advice. Deterministic, no AI, nothing stored. Needs sign-in: runs with an AICTIONBOT™ Werkbank licence; without a licence one check per connection every 30 days is free (sign in with “Connect without a licence”).

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_expenses"
  }
}

Input Schema

NameRequiredDescriptionDefault
tripsNoRows: employee, start, end, hours, destination (or country and city), km, vehicle, meals_claimed, travel_claimed, hotel_claimed, nights, receipt, meals_provided. German column names work too.
languageNoLanguage of the answer. Default de.
destinationNoWithout trips: a country or city whose rates to show, for example "Milan" or "Denmark".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, but the description adds traits they cannot convey: rates are hard-fixed with source and date (nothing fetched), the tool is deterministic with no AI and stores nothing, and it discloses the auth model and the 30-day free-tier limit. That is exactly the kind of extra behavioral context the annotations leave open.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The core purpose and rules are front-loaded, which is good, but the single dense paragraph is overloaded with branding ('AICTIONBOT™ by KULIC Advisory (tool 51)'), redundant rate arithmetic, and licensing boilerplate. Every rate detail earns some place, yet the marketing framing and run-on structure dilute readability.

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 complex domain tool with no output schema, the description fully covers inputs, the exact rate rules, the extra checks performed (double submissions, overlaps, missing receipts, weekends), and the return shape (red/yellow findings, claimed vs. allowed per person and total). Nothing an agent needs to call it correctly is missing.

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?

Schema coverage is 100%, so the baseline is 3, but the description goes beyond it: it explains the semantics of the trip row fields (hours only for one-day trips, meals_provided as '2 breakfasts', German column names accepted), the destination-only fallback mode, and the language default. It adds real meaning rather than restating field names.

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 (checks a travel expense list against official German per diem, mileage, and overnight rates) and enumerates the exact rules applied. An agent can distinguish this from the many other check_* siblings by the expense/per diem domain alone, and the dual mode (list check vs. destination rate lookup) is spelled out.

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?

Clearly explains the two operating modes: supply a trips list to run checks, or supply only a destination to get its rates, plus the licence/free-quota condition and the 'not tax advice' caveat. It never names an alternative sibling tool or states when-not to use this, so it falls short of a 5.

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.