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

Goes well beyond the annotations (idempotentHint/destructiveHint/readOnlyHint): it discloses that the customer number is server-assigned and returned, that existing records are never overwritten or deleted, that corrections happen out-of-band in Meistron, that ambiguous same-name matches result in no change, and that email/phone fields are gated behind a 'full autonomy' confirmation. These are exactly the behavioral traits an agent needs before invoking a mutation.

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?

Front-loaded with the core action and the required/optional split, followed by the dedup rules and then the permission-gating paragraph. It is long, but given the conditional write behavior and the sensitive contact-data gating, almost every sentence carries decision-relevant information; only the invoice-channel detail at the end is arguably tangential.

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 mutation tool with no output schema, the description supplies what is missing: it states what the response returns (the customer number) and full dedup/idempotency behavior. Combined with the annotations covering the safety profile, an agent has everything needed to call it 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 description coverage is 67%, so the schema documents most fields; the description adds the semantic that only 'name' is needed while 'Firma/Anschrift' are optional top-ups, and explains the deep gating condition on email/telefon/mobil. It does not add meaning for the bare ort/plz/strasse parameters, which remain undocumented in both places, keeping it just short of a 5.

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+resource ('Legt einen neuen Kunden an') and immediately clarifies scope with the optional-field note. It also implicitly distinguishes itself from the search/read siblings (kunden_suchen, auftraege_suchen) by describing dedup and write semantics rather than retrieval. An agent can tell exactly what this tool does without inspecting the 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?

It gives rich context for when the call is safe: only the name is required, and re-invoking with an existing name will not create a duplicate but will top up empty fields. However, it never names an explicit alternative (e.g. 'use kunden_suchen to check first') or states when NOT to call it, so there is clear context but no routing to siblings.

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