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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses the concrete return shape and a deliberate limitation: it returns Kennung, Kundennummer, Name, Ort, and whether an email exists, but intentionally not contact data. It also explains why the address is not needed for sending. This is valuable behavioral context not available from the schema or annotations.

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 front-loaded with the core purpose, followed by a crisp workflow warning and a focused explanation of output limitations. Each paragraph earns its place: no filler, but enough detail to prevent misuse.

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 read-only search tool with two optional parameters and no output schema, the description covers the search inputs, the returned fields, the key workflow prerequisite, and the intentional absence of contact details. An agent has everything it needs to select and invoke the tool 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 100%: the `suche` parameter already explains partial name/company/location matching and the default listing of most recently created records, and `anzahl` already states default and limit. The description repeats the search criteria but adds no new parameter-specific information beyond what the schema provides, so the baseline of 3 is appropriate.

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 Kunden des Betriebs nach Name, Firma oder Ort und nennt ihre Kennung.' It clearly states what the tool searches by and what it returns, and it distinguishes itself from the creation tool by emphasizing that this lookup supplies the Kennung needed by other tools.

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 guidance is explicit and emphatic: 'ZUERST SUCHEN, DANN ANLEGEN.' It directly warns against using `kunde_anlegen` without searching first, explaining the duplicate-customer consequence. This tells an agent exactly when to use this tool versus the sibling creation tool.

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