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

Annotations declare readOnlyHint=false and idempotentHint=false, and the description adds meaningful context beyond them: 'KODEN postar' (the call performs the posting), the booking-cap constraint, and detailed settle behavior including which accounts absorb FX differences (7960 loss / 3960 gain). It does not state reversibility or repeat-call behavior explicitly.

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?

It is front-loaded with the action and preconditions, then the argument list. Dense but every clause carries information given the low schema coverage; it is a long single block rather than cleanly segmented, which costs it a point.

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 non-idempotent mutation with no output schema, the description supplies preconditions (scope, cap), the argument semantics, and the FX handling — enough to invoke correctly. It stops short of covering failure modes or what happens on repeated calls.

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 only 17% (essentially just orgnr), so the description carries the load: it documents pay_date format (YYYY-MM-DD), bank_account as the credited cash account with default 1930, and full settle semantics where amount_ore means SEK actually paid. It adds little for invoice_id, hence not a 5.

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 states a specific verb+resource: 'Bokför en leverantörsbetalning på en faktura' (book a supplier payment against an invoice). Combined with the name register_supplier_payment, this clearly differentiates it from siblings like book_supplier_invoice, reverse_supplier_payment, and register_customer_payment.

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?

It states real preconditions: requires scope book and a booking cap that must not be exceeded (0 = no limit). This tells the agent when the call will succeed but does not explicitly name alternative tools (e.g. reverse_supplier_payment) or contrast use cases.

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