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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real value beyond that: the data source and its as-of date (Bundesnotarkammer/notar.de, 2026-10-20), the 10-result cap, the prohibition on full-directory retrieval, the absence of an API key, and that responses come back in German as text or JSON. Result-count behavior on overflow (truncation vs. error) is the one gap.

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 lead sentence is well front-loaded, but the second line ("Notare an einem Ort oder einer Postleitzahl, wahlweise mit Fremdsprache oder Namen.") is a near-verbatim repeat of the opening and earns nothing. The trailing human-calculator link and the German-response note are useful but could be consolidated with the format explanation instead of standing as separate fragments.

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, no output schema, and a 10-hit cap, the description does the heavy lifting an output schema would otherwise do: it lists the returned fields, the data source and date, the response language, and the output format choice. Only edge behavior (zero results, what happens at the 10-hit boundary, postalCode-plus-city ordering) is left unstated.

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 every parameter including the city/postalCode precedence rule and the language list. The description restates the requirement ("city oder postalCode ist nötig; language und name grenzen ein") but adds no syntax or precedence detail beyond the schema, so baseline 3 applies. The field enumeration is about outputs, not parameters.

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 specific verb and resource ("Findet Notare an einem Ort oder einer Postleitzahl in Deutschland") and even enumerates the returned fields (Name, Amtsbezeichnung, Anschrift, Fremdsprachen, Website, Link). It is unambiguous what the tool does, but it never names a related sibling such as notarkosten, so an agent must infer that this is a lookup and that one is a cost calculation.

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?

Usage is implied rather than stated: the agent learns that city or postalCode is required and that language and name narrow the result, and that a broad sweep is disallowed ("kein Abruf des ganzen Verzeichnisses", max 10 hits). There is no explicit statement of when to prefer this over a sibling tool and no guidance on what to do when a query returns nothing.

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