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.
Add one secure layer between your agents and this server.
Each tool addresses a distinct indoor-climate or energy question: subsidy eligibility, cooling load, window sealing, device selection, heating load, heatwave outlook, running costs, guide retrieval, and dew-point ventilation. Only geraet_wahl vs btu_empfehlung could be muddled by an agent, but their descriptions explicitly layer one above the other.
Tool names follow a mostly predictable lowercase underscore pattern with German domain nouns, e.g. btu_empfehlung, heizleistung_watt, taupunkt_lueften. The two ratgeber tools are verb-like (ratgeber_suche, ratgeber_lesen) rather than noun phrases, which is a minor deviation but still readable.
Ten tools is well within the ideal range and each tool pulls its weight for a specialized climate-advice server. The set covers calculations, forecasts, content search, and content retrieval without padding.
The domain is well covered: sizing for cooling and heating, device selection, running costs, window sealing, ventilation/dew point, heatwave info, subsidies, and citable guides. A live current-weather or humidity-observation tool would round out the 'weather' side, but agents can work around that gap.