Superseded by io.github.f-tiger/hvac-btu-heat-klimaanlage — same server, same URL.
Scored across 10 tools
Each tool covers a clearly distinct task: sizing, cost, sealing, decision support, ventilation, subsidies, heatwave forecast, or guide retrieval. There is no overlap or ambiguity between the calculation tools, the decision layer, or the search/read pair.
All tool names follow the same lowercase snake_case German compound style, such as btu_empfehlung, heizleistung_watt, and ratgeber_suche. No conventions are mixed, and the pattern is predictable once a few tools are seen.
Ten tools is a well-scoped size for a niche advisory server. Each tool covers a meaningful query type without redundancy or bloat, and the count feels appropriate for the domain.
The tool set covers device selection, heating and cooling sizing, electricity costs, window sealing, ventilation, subsidies, heatwave outlook, and guide access. One minor gap is the lack of a dedicated dehumidifier sizing tool, but dehumidifier guidance is still reachable through the generic decision and guide-search tools.
Balkonkraftwerk-/Speicher-Förderung in Deutschland (Stand 08/2026) und wie ein Zuschuss die Amortisation verkürzt. — German subsidies for plug-in balcony solar and storage: which state programmes exist, the ~100 € storage bonus, the apply-BEFORE-buying rule most programmes enforce, and the payback arithmetic with and without a grant. No federal purchase premium — only the VAT exemption.
| Name | Required | Description | Default |
|---|---|---|---|
| preis_eur | No | Kaufpreis des Speichers/Sets in € für die Amortisationsrechnung (optional) | |
| bundesland | No | Bundesland, z. B. 'Sachsen' oder 'Berlin' — German federal state (optional; ohne Angabe wird die Gesamtlage beschrieben) | |
| zuschuss_eur | No | Erwarteter Zuschuss in € (optional, Default 0) | |
| ersparnis_eur_jahr | No | Jährliche Stromersparnis in € (optional, Default 100 — typisch 60–120 € bei 1–1,5 kWh/Tag Verschiebung) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the tool's informational nature, what it covers (state programmes, payback arithmetic) and explicitly states what it does not cover ('No federal purchase premium — only the VAT exemption'). This gives a clear behavioral profile without contradictions.
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 description is compact and front-loaded, starting with the main topic and key details. It includes both German and English explanations, which adds a bit of redundancy but remains efficient. There is no wasted prose, and it effectively uses two sentences to convey substantial information.
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 tool with 4 optional parameters and no output schema, the description is highly complete: it explains the subject matter, the scope, exclusions, and hints at the calculation feature. Combined with the comprehensive schema, it gives the agent enough context to select and use the tool correctly.
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 coverage is 100%, with each parameter clearly described in the input schema. The description reinforces the payback context (e.g., ~100€ bonus) but does not add significant detail beyond the schema about individual parameters. Given high schema coverage, the baseline of 3 is appropriate.
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?
The description uses a specific verb ('Förderung... und wie ein Zuschuss die Amortisation verkürzt') and resource ('Balkonkraftwerk-/Speicher-Förderung in Deutschland'), clearly stating what the tool does: informs about state subsidies and calculates payback impact. It distinguishes itself from siblings by focusing on subsidies and payback arithmetic, which none of the sibling tools cover.
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?
Provides clear context by specifying the geographical scope (Germany), the types of subsidies (state programmes, ~100€ storage bonus, VAT exemption), and exclusions (no federal purchase premium). While not explicitly naming alternative tools, the scope is well-defined so an agent can infer when this tool is appropriate versus the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Empfohlene Kühlleistung (BTU) für einen Raum, mit passender Geräteklasse. — Recommended cooling capacity in BTU for a room, with the matching device class: how many BTU do I need for X m²? Same formula as the calculator on getecoback.com (340 BTU/m² × sun factor), for Germany and Europe.
| Name | Required | Description | Default |
|---|---|---|---|
| qm | Yes | Raumfläche in m² — room floor area in square metres (4–120) | |
| sonne | No | Sonneneinstrahlung — sun exposure: wenig = low/shaded, normal, viel = strong (south/west or top floor). Default: normal |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the calculation formula (340 BTU/m² × sun factor), the regional scope, and the output (BTU plus device class). This goes beyond a simple 'calculates BTU' and helps the agent understand internal logic, though it doesn't specify exact output formatting or error handling.
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 description is concise, containing only two main clauses, and is front-loaded with the core purpose. The bilingual repetition (German and English) is slightly redundant but not wasteful; it ensures clarity for a wider audience while keeping the description compact.
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 simple two-parameter calculation tool with no output schema and no annotations, the description is fairly complete. It explains what is returned (BTU and device class), the formula, and the target region. It doesn't describe the exact return data structure, but the simplicity of the tool makes this less critical.
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?
The input schema already covers 100% of parameters with descriptions, but the description adds the formula (340 BTU/m² × sun factor), which clarifies how 'qm' and 'sonne' are used in the calculation. This extra semantic detail enriches understanding beyond the bare schema.
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?
The description clearly states the tool's function: recommending cooling capacity in BTU for a room, including the matching device class. It uses specific verbs ('recommended', 'how many BTU do I need') and distinct resource ('cooling capacity in BTU for a room'), which distinguishes it from sibling tools like heizleistung_watt (heating) and klimaanlage_stromkosten (costs).
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?
The description gives an explicit usage scenario ('how many BTU do I need for X m²?') and specifies the target region (Germany/Europe). It doesn't name alternative tools, but the uniqueness of the cooling capacity calculation is clear enough for an agent to select this tool over its siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Benötigte Länge einer Fensterabdichtung für mobile Klimaanlagen aus den Flügelmaßen. — Required window-seal length for a portable air conditioner from the sash measurements (perimeter = 2×(width+height)), plus the off-the-shelf size that fits. Covers tilt-and-turn and roof windows.
| Name | Required | Description | Default |
|---|---|---|---|
| hoehe_cm | Yes | Flügelhöhe in cm (20–300) | |
| breite_cm | Yes | Flügelbreite in cm (20–300) — der bewegliche Teil, nicht der Rahmen | |
| fenstertyp | No | Fenstertyp — window type: kipp/drehkipp = tilt or tilt-and-turn, dachfenster = roof/skylight. Default: kipp |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, and it does convey the core calculation (perimeter formula) and output (length plus off-the-shelf size). However, it claims to cover only 'tilt-and-turn and roof windows' while the schema includes 'kipp' (tilt-only) as the default type, which is an incomplete and potentially misleading coverage statement. This gap in transparency is significant for a tool with no annotations.
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 description is concise, with two sentences in German and English that pack all essential information: purpose, formula, output, and supported window types. It is front-loaded and every phrase contributes, avoiding fluff or redundancy beyond the intentional bilingual presentation.
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?
Given the tool's moderate complexity (3 params, no output schema, no annotations), the description covers the main aspects: what it calculates, how (formula), and what it returns (length and off-the-shelf size). It could be more complete by stating the units of the output or explicitly listing all supported window types, but it is still sufficiently complete for a straightforward calculation tool.
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 baseline is 3. The description adds value beyond the schema by explaining that the length is derived from the sash perimeter (2×(width+height)), reinforcing that 'breite' is the movable part (as schema already notes) and that 'fenstertyp' influences the available coverage. This clarifies how parameters relate to the computation.
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?
The description clearly states it calculates the required window-seal length from sash measurements, provides the perimeter formula (2×(width+height)), and indicates it also returns the off-the-shelf size that fits. This specific verb+resource distinguishes it from siblings like btu_empfehlung or heizleistung_watt, which address other aspects of portable AC selection.
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?
The description gives clear context: it is for portable air conditioners, based on sash measurements, and covers specific window types. It does not explicitly mention when not to use the tool or alternatives, but the context is sufficient since the sibling tools serve clearly different purposes (BTU, power, costs, guides, etc.). A minor omission is that it does not mention the 'kipp' (tilt-only) window type despite its default in the schema.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Welches Gerät löst mein Raumklima-Problem? — Which device family solves a given indoor-climate problem (too hot, damp/mould, too cold, stale air), with the honest physics, the right size for the room and the matching guide. The decision layer above btu_empfehlung/heizleistung_watt.
| Name | Required | Description | Default |
|---|---|---|---|
| qm | No | Raumfläche in m² — room floor area in square metres (4–120). Default: 20 | |
| problem | Yes | Das Problem — the problem: zu_heiss = room too hot, feucht_schimmel = damp air / condensation / mould risk, zu_kalt = room too cold (no fixed heating), stickige_luft = stale air / odours |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral disclosure burden. It communicates that this is an advisory/decision tool returning a device family, sizing, and a matching guide, and it adds an honesty expectation via 'honest physics'. However, it does not describe output format, assumptions, or possible side effects, which leaves some behavioral gaps.
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?
A single bilingual sentence packs purpose, scope, quality promise, and sibling relations efficiently. Some redundancy exists because the first clause is essentially repeated in English, and 'honest physics' is slightly vague, but the description remains economical and front-loaded.
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 simple 2-parameter tool with complete schema descriptions and no output schema, the description names expected outcomes (device family, size, matching guide) and situates itself among related tools. It does not specify the exact return format or how the matching guide is provided, but this is a minor gap for a decision-layer recommendation tool.
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 already documents the problem enum and the qm unit, range, and default. The description's mention of 'the right size for the room' reinforces qm's role but adds no concrete semantic detail beyond the schema. Baseline 3 is appropriate.
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?
The description states a concrete decision task ('Which device family solves a given indoor-climate problem'), lists the specific problem categories it covers, and explicitly distinguishes it from sibling tools by calling it 'the decision layer above btu_empfehlung/heizleistung_watt'. This makes the tool's purpose clear and differentiated.
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?
The phrase 'decision layer above btu_empfehlung/heizleistung_watt' gives useful navigational context, implying this tool is the family-level recommendation step before detailed calculation tools. It does not explicitly state when not to use it or name alternative conditions, so it stops just short of full exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Benötigte Heizleistung in Watt für einen Raum (Infrarot/Elektro). — Required heating power in watts for a room, from floor area and insulation standard (60/80/100 W/m² for new build, existing, old building), including running cost per full-load hour.
| Name | Required | Description | Default |
|---|---|---|---|
| qm | Yes | Raumfläche in m² (1–100) | |
| daemmung | No | Dämmstandard: gut = Neubau (60 W/m²), mittel = Bestand (80), schlecht = Altbau (100). Default: mittel | |
| strompreis_euro_kwh | No | Arbeitspreis in €/kWh für die Betriebskosten (Default: 0.30) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full burden. It does disclose the calculation basis (60/80/100 W/m²) and the inclusion of running cost, but it does not mention potential assumptions (e.g., standard room height) or limitations of the estimate. This is moderate transparency for a calculator tool.
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 description is compact, front-loading the core purpose, and includes useful detail in two sentences. The bilingual repetition (German and English) introduces slight redundancy but does not detract significantly from conciseness.
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 simple calculator with no output schema or annotations, the description covers the essential inputs, the calculation basis, and the output components (watts and running cost). It omits fine details like output formatting or caveats, but given the low complexity, it is reasonably complete.
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?
The input schema already provides full descriptions for all three parameters, including the W/m² mapping for the enum. The description adds little beyond restating that floor area and insulation are inputs, so it does not significantly enhance parameter understanding beyond the schema's high coverage.
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?
The description clearly states the tool provides required heating power in watts for a room based on floor area and insulation standard. It also specifies the inclusion of running cost per full-load hour, which distinguishes it from sibling tools like btu_empfehlung that likely focus on BTU units.
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?
The description implies usage when a user needs heating power in watts with floor area and insulation data, but it does not explicitly mention when to use this tool over alternatives (e.g., btu_empfehlung) or any exclusions. No direct guidance or alternative references are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Live-Hitzevorschau für Deutschland (nächste 3 Tage). — Live heatwave outlook for Germany: highest temperature over the next three days across Berlin, Frankfurt and Munich (open-meteo), flagged from 28 °C and 32 °C.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even though no annotations exist, the description discloses the key behavioral aspects: the time span (3 days), locations (3 cities), data source (open-meteo), and warning thresholds (28°C and 32°C). It doesn't mention that it's read-only, but the concept of an outlook implies it only returns data; this is adequate for a no-parameter tool.
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 description is a single bilingual sentence, about 25 words, that covers all the necessary facts without redundancy. It front-loads the purpose and adds precision.
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?
The tool is simple (no params, no output schema) and the description covers the essential information: what it computes and for which locations. It could be clearer on how the output is formatted (e.g., a list of temperatures), but this is a minor gap for such a straightforward tool.
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?
With zero parameters, the schema is fully self-contained. The description adds value by explaining what the tool provides, which contextualizes the expected input (none).
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?
The description explicitly states the tool's function: providing a live heatwave outlook for Germany over the next three days, with specific thresholds and cities. This is clearly distinct from sibling tools about building energy efficiency, so an agent can select it unambiguously.
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?
The context is clear: use this tool to retrieve a heatwave forecast for Berlin, Frankfurt, and Munich. However, unlike the get_calls example, it does not name alternative tools or specify when not to use it, so it lacks explicit usage boundaries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Stromkosten eines Klimageräts. — Running cost of an air conditioner or any appliance: watts × hours × electricity price × compressor duty cycle. What does it cost to run per hour, per day, per month?
| Name | Required | Description | Default |
|---|---|---|---|
| tage | No | Anzahl Tage (Default: 30) | |
| watt | Yes | Leistungsaufnahme in Watt (z. B. 1000) | |
| auslastung | No | Kompressor-Auslastung 0–1 (Default: 0.65) | |
| stunden_pro_tag | Yes | Betriebsstunden pro Tag | |
| strompreis_euro_kwh | Yes | Arbeitspreis in €/kWh (z. B. 0.30) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden. It explains the calculation formula (watts × hours × price × duty cycle) and the outputs (cost per hour/day/month). This is sufficient for a pure calculation tool with no side effects, though it doesn't mention defaults or edge cases.
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 description is concise and front-loaded, with the key concept in the first sentence. It includes the formula and output periods without fluff. Some redundancy exists due to bilingual repetition, but it remains efficient and readable.
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 simple calculator with no output schema and no annotations, the description is complete: it states the formula, inputs, and outputs. It gives enough context for an agent to invoke correctly and interpret results without needing further explanation.
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 coverage is 100%, so baseline is 3. The description adds value by linking parameters to the formula—identifying auslastung as compressor duty cycle and clarifying that elapsed time is hours per day. This goes beyond the schema's individual descriptions.
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?
The description clearly states a specific purpose: calculating running costs for an air conditioner or any appliance, with a formula. It distinguishes itself from sibling tools like heizleistung_watt and btu_empfehlung, which address other HVAC metrics.
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?
The description provides clear context on when to use the tool (to determine electricity costs of running an appliance) and the core calculation approach. It doesn't explicitly exclude alternatives or compare with siblings, but the intent is unambiguous given the sibling tools are about sizing/heat, not costs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Liefert den Volltext eines einzelnen Ratgebers als Klartext. — Returns the full plain text of one guide from getecoback.com so the answer can be written from the source and cited. Pass a path or URL from ratgeber_suche.
| Name | Required | Description | Default |
|---|---|---|---|
| pfad | Yes | Pfad oder vollständige URL, z. B. /guide/klimaanlage-kippfenster.html |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It states it returns the full plain text of one guide, implying a read-only operation. It adds context about the source (getecoback.com) and the intended use (citation), but does not cover error handling or HTTP behavior. This is adequate for a simple retrieval tool, but not exhaustive.
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 description is brief and bilingual, with each sentence providing distinct information: core function, purpose/context, and input source. No filler or redundancy, despite the language repetition.
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?
The tool is simple with one parameter and no output schema. The description covers the core behavior, input format, and intended use. It lacks explicit error behavior or return type specifics, but for a single-guide retrieval tool, it is fairly complete. A small gap exists around what happens for invalid paths.
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?
The schema describes 'pfad' as a path or full URL with an example. The description adds that the path/URL should come from ratgeber_suche, which is a key constraint not present in the schema. This enriches the parameter semantics.
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?
The description clearly states the tool's function: 'Liefert den Volltext eines einzelnen Ratgebers als Klartext' and 'Returns the full plain text of one guide from getecoback.com'. It distinguishes itself from sibling ratgeber_suche by specifying it retrieves a single guide's full text, and even references ratgeber_suche as the source for paths.
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?
The description explicitly instructs 'Pass a path or URL from ratgeber_suche', establishing a clear workflow: search first, then read. It also explains the purpose 'so the answer can be written from the source and cited'. This provides strong guidance on when and how to use the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Durchsucht die Ratgeber von getecoback.com und gibt Titel, URL und Kurzbeschreibung zurück. — Searches this site's guides on air conditioning, window sealing, ventilation, heating, dehumidifiers and electricity costs, returning title, URL and summary for each match — citable sources for the answer.
| Name | Required | Description | Default |
|---|---|---|---|
| max | No | Anzahl Treffer (1–10, Default: 5) | |
| frage | Yes | Suchbegriff oder Frage — search term or question, German or English, e.g. 'Klimaanlage Kippfenster abdichten' or 'portable ac tilt window' | |
| sprache | No | Nur deutsche oder nur englische Seiten (Default: beide) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses return fields (title, URL, summary) and topic scope, which is helpful, but it doesn't specify how search works (e.g., full-text vs title-only), result ordering, or any limits beyond those in the schema. The read-only nature is implied but not explicitly stated.
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 description is a single sentence with a bilingual translation. It is brief and front-loaded, but the English translation is redundant for an agent that can handle German. Still, it is efficient and easy to parse.
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?
With no output schema, the description adequately covers return values and topic scope. However, it doesn't connect to sibling tools (e.g., how to use the URL with ratgeber_lesen) or mention potential pitfalls. It is complete for a search tool but misses cross-tool guidance.
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 coverage is 100% with bilingual descriptions and examples for all parameters. The description adds no extra parameter semantics beyond the schema, so baseline 3 is appropriate.
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?
The description clearly states it searches the site's guides on specific topics (air conditioning, window sealing, etc.) and returns title, URL, and summary. This distinguishes it from sibling tools like ratgeber_lesen (which reads a guide) and the various calculators.
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?
The description implies use for finding citable sources related to the listed topics. It gives a clear use case but doesn't explicitly exclude other contexts or mention when to prefer alternatives. A note on using this before ratgeber_lesen would make it stronger.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Taupunkt der Außenluft und die Antwort auf 'darf ich jetzt lüften?'. — Dew point of the outside air and whether opening the window right now would make a basement or damp room wetter (Magnus formula, walls counted 2 °C below room temperature).
| Name | Required | Description | Default |
|---|---|---|---|
| innen_temp_c | Yes | Innen-/Kellertemperatur in °C (Wände werden 2 °C kühler gerechnet) | |
| aussen_temp_c | Yes | Außentemperatur in °C | |
| aussen_luftfeuchte_prozent | Yes | Relative Luftfeuchte außen in % (5–100) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral burden. It discloses the Magnus formula and the assumption that walls are calculated 2 °C below room temperature. It does not describe the output format, but these details add meaningful transparency beyond a simple 'calculates dew point'.
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 description is compact and front-loaded, with the German purpose followed by the translated/expanded English version. Both parts contribute: the first states the answer to 'should I ventilate?', and the second adds the formula and wall assumption.
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 simple three-parameter calculation tool with no output schema, the description provides enough context: inputs are fully documented in the schema, and the calculation logic is stated. It does not specify the return format, but this is a minor gap.
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 coverage is 100%, so the baseline is 3. The description repeats the wall temperature assumption already present in the innen_temp_c parameter description and adds no new parameter-specific meaning.
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?
The description clearly states the tool computes the dew point of outside air and answers whether opening a window would make a basement or damp room wetter. This specific outcome distinguishes it from sibling tools like heating load or heat wave preview.
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?
The description provides a clear use case: deciding if ventilating now would worsen dampness in a basement or damp room. It does not explicitly mention alternatives or exclusions, but the context is distinct enough from siblings.
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.
geraet_wahlbalkonspeicher_foerderungbtu_empfehlung2 fields changedInput schema / properties / qm / descriptionPrevious value: -"Raumfläche in m² (4–120)"New value: +"Raumfläche in m² — room floor area in square metres (4–120)"Input schema / properties / sonne / descriptionPrevious value: -"Sonneneinstrahlung des Raums (Default: normal)"New value: +"Sonneneinstrahlung — sun exposure: wenig = low/shaded, normal, viel = strong (south/west or top floor). Default: normal"fensterabdichtung_laenge1 field changedInput schema / properties / fenstertyp / descriptionPrevious value: -"Fenstertyp (Default: kipp)"New value: +"Fenstertyp — window type: kipp/drehkipp = tilt or tilt-and-turn, dachfenster = roof/skylight. Default: kipp"ratgeber_suche1 field changedInput schema / properties / frage / descriptionPrevious value: -"Suchbegriff oder Frage, z. B. 'Klimaanlage Kippfenster abdichten' oder 'portable ac tilt window'"New value: +"Suchbegriff oder Frage — search term or question, German or English, e.g. 'Klimaanlage Kippfenster abdichten' or 'portable ac tilt window'"ratgeber_lesenratgeber_sucheheizleistung_watttaupunkt_lueftenbtu_empfehlungfensterabdichtung_laengehitzewelle_vorschauklimaanlage_stromkostenSuperseded by io.github.f-tiger/hvac-btu-heat-klimaanlage — same server, same URL.
BTU sizing, window-seal length, heatwave outlook, running costs, balcony solar subsidies (DE/EU).
Weather forecasts from MET Norway (Yr): geocoding plus hourly forecasts worldwide.
Real-time weather conditions and multi-day forecasts via Open-Meteo — free, no API key required
Add one secure layer between your agents and this server.