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

No annotations are supplied, so the description carries the full behavioral burden. It discloses one substantive constraint — 'floor area alone cannot size a dehumidifier' — which prevents a misuse of the qm parameter, and 'Same decision rules as the website' signals deterministic advisory behaviour with no purchase or diagnosis. It does not state that the tool is read-only/advisory, what shape the returned 'next step' takes, or that it performs no remote diagnosis (that caveat only appears inside the schema).

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?

Two tight sentences with the framing question and the decision guidance front-loaded, then the damp-room caveat. Nearly every clause carries information; the only slight filler is the closing 'Same decision rules as the website', which supports trust but adds little actionable content.

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 five parameters, four enums and no output schema, the description needs to explain what an agent gets back. 'Choose a next step' is suggestive but does not say whether the result is a single recommendation, a ranked list, or a device category, and there is no mention of the conditional relevance of purpose/humidity/temperature. Adequate as a framing statement, incomplete for a decision engine whose return value is undocumented.

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 every parameter is already documented in detail, including defaults and the explicit note that qm applies to heating/cooling only. The description reinforces the dehumidifier caveat but adds no enum semantics, formatting, or interaction rules beyond the schema. Baseline 3 is appropriate when the schema does this much work.

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 opens with a German framing question and an English verb+resource statement: 'Choose a next step for heat, damp/mould, cold or stale air', which enumerates the four problem domains the tool handles. That is far more specific than the bare name 'geraet_wahl'. It stops short of 5 because it never positions itself against heat-related siblings such as btu_empfehlung or heizleistung_watt, so an agent cannot tell from the text alone whether this tool or those should be called first.

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?

It gives real conditional guidance: for damp rooms the rule is 'measure first, investigate damage and compare cold-room or laundry conditions before buying', which sets an ordering of steps. It also implicitly scopes usage to the four enumerated problem types. What is missing is any explicit routing to alternatives — no statement like 'for dehumidifier sizing continue here, for heater wattage use heizleistung_watt'.

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