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

Adds substantial behavior beyond the destructiveHint annotation: the record is always a draft, never sent or booked, and stays editable. This meaningfully reframes the risk profile of a write operation. It stops short of emphasizing that a persistent record is still created (relevant given destructiveHint=true) or noting auth/permission 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?

Front-loads the single most important fact (draft, never sent/booked) before parameter guidance, and every clause carries information. Sentence flow is dense with em-dashes and parentheticals, which slightly hurts scannability but there is no 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 an 18-parameter mutation with no output schema and only a bare destructiveHint annotation, the description covers the tricky semantics (status, contact_person_id, tax rule selection) well. It does not state what the call returns (invoice id), which is the only notable omission.

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 baseline is 3, but the description adds real meaning on top: it clarifies contact_person_id is a sevdesk USER (not the contact) sourced from an existing invoice, and explains the tax_rule_id vs tax_type split with '1 = the usual choice'. These clarifications resolve ambiguities the schema alone leaves open.

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 (create), resource (invoice type RE), and the crucial scope constraint that it is ALWAYS saved as a DRAFT (status 100). An agent immediately knows this produces an editable, unsent invoice rather than a finalized one, which is the key distinction for this tool.

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 concrete when-to-use routing: use tax_rule_id on 2.0 accounts and tax_type on 1.0 accounts, checking via sevdesk_get_bookkeeping_system_version, and retrieve contact_person_id via sevdesk_get_invoice. It lacks any explicit when-not-to-use or alternative-tool exclusion, but provides clear operational context.

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