list_cost_locations

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description tells us it's a read-only operation ('Ruft... ab' indicates retrieval without side effects) and the scope (all cost centers for a customer). However, it doesn't describe any restrictions, such as potential large result sets, ordering, or whether the read is always consistent. For a simple list operation, this is adequate but not rich; the absence of a note about not requiring the API key if the environment variable is set is notable, as the schema provides that context.

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 a single, concise sentence that efficiently conveys the tool's purpose without any waste. It doesn't repeat the tool name artificially or include filler. Every word serves a purpose. For such a simple tool, this is ideal conciseness.

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?

Given that the tool is a simple list operation with 1 optional parameter and no output schema, the description is nearly complete. It covers what and for whom ('eines BuchhaltungsButler-Kunden'). The only minor gap is that it could mention that no API key means it uses the environment variable, but that's already in the schema's parameter description. The description doesn't need to describe return values as there's no output schema, and the operation is straightforward. Given the low complexity, the description is sufficiently complete, though a tiny bit more (e.g., 'in alphabetical order' or 'including archived cost centers') could lift it to a 5.

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 single parameter 'api_key' has a clear description explaining it's the customer's API key and is optional if an environment variable is set. The description 'Ruft alle Kostenstellen...' doesn't add parameter-specific information beyond the schema. Per the rubric, the baseline for 100% coverage is 3, and no additional meaning is added by the description, so a 3 is correct.

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 'Ruft alle Kostenstellen eines BuchhaltungsButler-Kunden ab' clearly states the action ('Ruft alle... ab' = retrieves all cost centers) and the resource ('Kostenstellen' = cost centers of a BuchhaltungsButler customer). It is specific and uses a clear verb+resource structure. It does not explicitly distinguish itself from the sibling 'create_cost_location', but the read vs. write distinction is easily inferable from the verb, so it earns a 4 rather than a 5.

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 description implies when to use this tool (when you need to list all cost centers for a customer) through the present tense 'Ruft... ab'. It does not explicitly state when not to use it or name alternatives, but the sibling context (create_cost_location) implies the read-versus-write boundary. Given the tool's simplicity, the implied usage is reasonably clear, though explicit exclusions are missing, so a 4 is appropriate.

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