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

Annotations only declare the safety profile (non-destructive write, open world); the description adds substantial behavioral context beyond them — that the invoice is persisted but mutable, not booked or sent, that it returns number and totals, that each call is confirmed by default, and that it reaches other people / requires the Cotlet API key. This is exactly the extra context annotations do not carry.

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 scoping is front-loaded, but 'It is saved, not booked and not sent' is stated and then restated in the following sentences, and the confirmation/API-key sentences add length. There is measurable redundancy that a tighter version could trim.

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 no output schema, the description usefully notes it returns the invoice number and totals, and it covers confirmation behavior and auth requirements. For a write tool in this context it is nearly complete, with only minor param-level detail lacking.

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 both required and optional parameters are already documented. The description restates row requirements and the invoice/due-date defaults, which largely duplicates the schema rather than adding syntax or format detail. Baseline 3 applies.

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 (save/create a customer invoice) and immediately distinguishes it from siblings by clarifying it is saved, not booked and not sent, naming bookkeep_invoice and send_invoice as the later steps. An agent can tell this apart from the other Fortnox invoice tools 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?

Explicitly describes the condition that selects this tool versus its siblings: use it to create a saved/editable invoice, and only run bookkeep_invoice / send_invoice later. It also states the confirmation requirement and API-key prerequisite, leaving little to inference.

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