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

With no annotations, the description carries the full burden and does disclose real behavior: the 2–5 range, the not_reported sentinel for missing substances, and the deliberate absence of ranking or aggregate scoring. It does not cover failure behavior for unrecognized slugs nor confirm read-only semantics, which keeps it below a 5.

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 sentences, both front-loaded: the operation and output shape come first, the exclusions second. No filler, and the parenthetical about WaterScore is tightly scoped to what it needs to say.

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 does the work of describing the return structure — per-substance rows with measurement date, limit, source, and not_reported for gaps. That is nearly complete for a read-only comparison tool; only error handling for invalid places is unaddressed.

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 schema already documents both parameters including the accepted slug/name/PLZ forms and the optional substance key. The description reinforces the 2–5 cardinality but adds no new semantics for the substance filter, so 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?

The description names a precise verb and resource ('Stellt die Werte des neuesten Prüfberichts von 2 bis 5 Orten nebeneinander') and states the exact scope: main supply, per-substance values with measurement date, limit and source. It also separates itself from per-city pages by noting the WaterScore lives only there, so an agent can distinguish this from the single-city quality tools without opening a schema.

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 2-to-5-place comparison scope gives a clear condition for use, and it explicitly excludes what the tool will not do (no ranking, no overall grade). It stops short of naming an alternative tool outright — the agent must infer that a single city belongs in get_water_quality — so it is clear context rather than full routing.

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