nkfix-mcp

Overview Schema Source Related Servers Discussions Admin

Hausgeld prüfen

check_hausgeld

Read-only

Verify a condominium's Hausgeld statement by checking tenant-allocable items under BetrKV, validating the unit's share calculation, and confirming totals. No data is stored.

Instructions

Prüft eine Hausgeld-Einzelabrechnung einer Eigentumswohnung: welche Positionen auf den Mieter umlagefähig sind (BetrKV), ob der eigene Anteil richtig berechnet ist und ob die Summe stimmt. Speichert nichts.

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": {
      "line_items": "<line_items>",
      "own_shares": "<own_shares>",
      "total_shares": "<total_shares>"
    },
    "name": "check_hausgeld"
  }
}

Input Schema

Name	Required	Description
`line_items`	Yes	die Positionen der Hausgeld-Einzelabrechnung der WEG
`own_shares`	Yes	Miteigentumsanteil der Wohnung, z. B. 125
`total_shares`	Yes	Summe aller Miteigentumsanteile, z. B. 1000
`statement_total`	No	Endsumme der Einzelabrechnung für die Summenprobe

Output Schema

Name	Required	Description
`notes`	Yes	Hinweise zum Abrechnungszeitraum und zu den Heizkosten
`sum_check`	Yes	nur mit statement_total
`line_items`	Yes
`owner_count`	Yes
`owner_total`	Yes	Summe dessen, was der Eigentümer trägt
`allocable_count`	Yes
`allocable_total`	Yes	Summe der umlagefähigen eigenen Beträge
`undecided_count`	Yes
`undecided_total`	Yes	Summe der eigenen Beträge der Positionen mit allocable=null

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A3.8/5.0

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 "Speichert nichts", so there is no contradiction. Beyond the annotations it discloses the actual validation logic (BetrKV allocability, own-share arithmetic, sum reconciliation), which is real behavioral content an agent cannot get from the annotations. It stops short of saying what happens when a check fails or how discrepancies are reported.

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 sentences, front-loaded with the verb and object, then the concrete checks, then the non-persistence caveat. Every clause adds information and nothing is repeated from the schema or annotations.

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?

With read-only annotations, 100% schema coverage and an output schema present, the description carries the right residual load: what is validated and that nothing is persisted, plus domain context (BetrKV, WEG). Minor gaps remain around prerequisites and failure reporting, but nothing needed for correct invocation is missing.

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 coverage is 100%, so the schema already documents line_items, own_shares, total_shares and statement_total with examples, making 3 the baseline. The description adds a little meaning by tying "eigener Anteil" and "Summe" to the checks performed, but it gives no guidance on how own_shares/total_shares drive the calculation or what statement_total should equal.

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?

The description names a specific verb and resource ("Prüft eine Hausgeld-Einzelabrechnung einer Eigentumswohnung") and enumerates the three checks performed: BetrKV tenant-allocation, correctness of the own share, and the sum check. It does not name any sibling such as precheck_statement, so the agent must infer the boundary itself, which keeps this at a 4 rather than a 5.

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 by the object being checked: it applies to a WEG Hausgeld-Einzelabrechnung, not to a rental statement or meter reading. There is no explicit when-not guidance, no mention of prerequisites (e.g. data needed from get_statement first), and no named alternative such as precheck_statement.

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