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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description adds substantial context beyond that: nothing is booked, no invoice number is consumed, the customer is never notified, the draft appears under Utkast in Salg → Faktura-/salgsoversikt, and it requires a Cotlet API key with app access. This is exactly the extra behavioral disclosure the annotations cannot 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?

Front-loaded with the core purpose, but it repeats itself: 'Nothing is booked and nothing is sent' is restated later as 'Nothing is booked, no invoice number is used and the customer hears nothing.' The UI navigation sentence is useful context but the duplication costs it here.

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?

There is no output schema, yet the description covers the return value (draft_id), the side-effect profile (nothing booked/sent), the follow-up path (create_invoice), and the auth requirement. An agent has everything needed to call and chain 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 coverage is 100%, so the schema already documents all seven parameters, including the detailed lines format, currency default, and date defaults. The description adds nothing parameter-specific beyond naming draft_id as the return handle, so the baseline of 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 an invoice draft for a customer') and immediately distinguishes it from the issuing sibling by naming create_invoice as the next step. An agent can tell it apart from fiken_create_invoice without opening 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?

Explicit routing: 'Pass the draft_id to create_invoice to issue it.' It also states that it 'runs without asking first' because nothing is booked or sent, which is a direct when-to-use / confirmation-policy signal. No alternatives are left unaddressed.

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