Heat-pump readiness check for German single-family houses: traffic light, reasons, next step
Scored across 1 tool
Only one tool exists, so there is no possibility of confusing it with another tool. Its purpose is clearly stated.
With a single tool, the name waermepumpen_vorcheck is self-descriptive and consistent with the server name. No mixed conventions possible.
One tool is borderline thin; a single orientation check could reasonably be split into an estimate call and a full-check link call, but it is coherent as a single focused operation.
The tool covers the stated orientation purpose (traffic light, heat load class, next step, link) but by design is not a full CRUD surface and has no follow-up operations, so the surface is intentionally minimal.
Schätzt, wie gut die Voraussetzungen für eine Luft-Wasser-Wärmepumpe in einem selbst bewohnten Einfamilien-, Doppel- oder Reihenhaus in Deutschland sind. Liefert eine Ampel (gruen/gelb/rot/unbekannt) mit Begründung, die Einordnung der Heizlast pro m² (niedrig/mittel/hoch), den wichtigsten nächsten Schritt und einen vorbefüllten Link zum vollständigen kostenlosen Check. Estimates heat-pump readiness of a German single-family house (traffic light, reasons, next step, link). Orientation only.
| Name | Required | Description | Default |
|---|---|---|---|
| test55 | No | Wurden an einem kalten Tag mit höchstens 55 °C Vorlauf alle Räume warm? teilweise = ein oder zwei Räume blieben kühl, nein = mehrere. Bei Fußbodenheizung nicht nötig. | |
| baujahr | No | Baujahresklasse des Gebäudes (nicht der Heizung) | |
| flaeche | No | Beheizte Wohnfläche in m² | |
| haustyp | No | Freistehend, Doppelhaushälfte (dhh), Reihenend- oder Reihenmittelhaus | |
| saniert | No | Bereits gedämmt/erneuert: Dach bzw. oberste Geschossdecke, Fenster, Außenwände, Kellerdecke | |
| verbrauch | No | Jahresverbrauch in der gewählten Einheit, aus der Jahresabrechnung | |
| brennstoff | No | Brennstoff und Einheit des Verbrauchs (Gas in kWh oder m³, Heizöl in Litern, Pellets in kg, Flüssiggas in Litern, Fernwärme in kWh, Heizstrom in kWh) | |
| heizsystem | No | Besonderheit der Wärmeverteilung: Gas-Etagenheizung (etage) oder Einrohrheizung (einrohr); sonst zentral | |
| warmwasser | No | Wird das Warmwasser mit derselben Heizung erwärmt? | |
| heizflaechen | No | Überwiegend Fußbodenheizung, Heizkörper, gemischt – oder keine (keine wassergeführte Heizung, z. B. Nachtspeicher/Elektro) | |
| verbrauch_ganzes_jahr | No | false, wenn der Verbrauch nicht für ein ganzes Jahr gilt | |
| abschlag_gas_eur_monat | No | Nur wenn kein Jahresverbrauch bekannt ist: monatlicher Abschlag für Gas in €. Wird als grobe Schätzung umgerechnet; sie kann die Einschätzung nie verschlechtern. |
| Name | Required | Description |
|---|---|---|
| link | Yes | |
| ampel | Yes | |
| titel | Yes | |
| hinweis | Yes | |
| begruendung | Yes | |
| heizlast_pro_m2 | Yes | |
| zusammenfassung | Yes | |
| naechster_schritt | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the description only needs to add domain caveats — and it does: the assessment is explicitly 'Orientatio only' and covers only self-occupied German houses. It also discloses the output shape (green/yellow/red/unknown with justification, plus a prefilled link), which is behaviorally useful even though an output schema exists.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The German sentences are front-loaded and information-dense with no filler. The trailing English sentence largely duplicates the German text, which is a small redundancy but also aids cross-language agents.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 12-parameter, zero-required, output-schema-bearing diagnostic tool, the description supplies the purpose, the output structure, the domain boundary (German, self-occupied, single/double/terraced) and the reliability caveat, while the schema (100% coverage) handles the inputs. Nothing an agent needs in order to decide to call it is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema itself carries all parameter meaning (units, enums, the 55 °C flow-temperature test, the gas-advance-payment fallback). The description adds nothing about the 12 parameters, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Schätzt') and a precise resource/scope: readiness of a German owner-occupied single-family, semi-detached or terraced house for an air-water heat pump. It also enumerates the concrete outputs (traffic light, heating-load class, next step, prefilled link), so an agent knows exactly what comes back.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Orientation only' plus the reference to a 'vollständigen kostenlosen Check' makes clear this is a rough pre-assessment, not a full analysis. There are no sibling tools to route between, but there is no explicit statement of when the tool should not be used (e.g., non-residential, rented, non-German buildings).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
waermepumpen_vorcheckSolar, weatherization, EV charging, battery and heat-pump decision tools for AI agents.
Heating, ventilation and energy engineering calculations and diagnostics for AI agents.
Wärmepumpe Kosten Europa: the site's own MCP server — dataset, enquiry (enquiry = a human...
Heat pump vs gas hot water (AU): rebate stack, net outlay and payback verdict by postcode.
Add one secure layer between your agents and this server.