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

With no annotations at all, the description carries the full burden and does well: it discloses the email side effect, that the invoice is free with no VAT under § 19 UStG, that a full address is mandatory above €250, and the defaults for billing.name and email. It does not say whether repeated calls are idempotent or what happens to a payment already invoiced, which matters for a creation tool.

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 conditional gate before any mechanics, then packed with the invoicing scope, side effect, and billing rules in a handful of clauses. No sentence is filler.

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 nested-object creation tool with no annotations and no output schema, this covers nearly everything an agent needs: when to call, what gets picked, that an email is sent, and the address threshold. Only the return shape (invoice ID/number) and repeat-call behavior are unaddressed, which are modest gaps.

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 25% (just api_key), so the description must compensate and does: it explains payment_ids' selection semantics, the email default, the billing.name default, and the €250 full-address rule. Individual billing subfields (street, city, vat_id, country, postal_code) remain undocumented, but their names are largely self-explanatory.

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 (creates an invoice, emails it) plus precise scope: payments that have none yet, or the given payment_ids. That scope immediately separates it from the sibling list_invoices, which only reads.

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?

'Only if you need an invoice' is an explicit when-to-use gate, and 'Nothing is invoiced unless you call this' rules out any assumption that invoicing happens automatically. It stops short of naming a specific alternative sibling or describing when-not (e.g. already-invoiced payments), so it is strong but not complete.

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