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

Annotations declare a non-read-only, non-destructive, open-world write, but the description adds real behavioral context beyond them: nothing is sent, nothing is booked, the invoice number is only provisional and is fixed later by send_invoice, and the user's Cotlet API key with app access is required. That is exactly the disclosure a mutation tool needs.

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 core is front-loaded, but the same idea is repeated: 'Nothing is sent and the invoice number is not final' is restated as 'The draft is not sent and not booked, and its number is only provisional'. The redundant sentence dilutes an otherwise efficient paragraph.

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?

No output schema exists, and the description supplies the context an agent needs: draft semantics, follow-up step, and auth requirement. It stops short of describing what the returned draft contains, but for a create call with full schema coverage this is close to complete.

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 all 7 parameters. The description only reinforces price_mode ('net or gross as you choose') and the position line semantics, which the schema already covers, so it adds little beyond the baseline.

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?

States a specific verb and resource ('Create an invoice as a draft with its positions') and immediately scopes it against the sibling 'send_invoice', which is named explicitly. An agent can distinguish this from sevdesk_send_invoice or sevdesk_create_contact 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?

Gives explicit when-to-use logic ('runs without asking first because it reaches nobody') and names the alternative step ('send_invoice is the step that does'). The draft-vs-final distinction is spelled out rather than implied.

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