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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing that the record is only a draft with no invoice number and requires user completion in Papierkram, and by quantifying cost (10 credits to create, 50 for an invoice) against a limited monthly quota. That is exactly the kind of side-effect and resource-cost context annotations cannot express.

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?

Three dense sentences, front-loaded with the 'WRITE:' action type and the draft-state caveat, then prerequisites, then verification and cost. No filler and nothing buried.

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 11-parameter mutation with no output schema, the description covers state semantics, required inputs, verification path, and credit cost, which is nearly everything an agent needs. The missing piece is minor: it doesn't mention all four required fields (name, customer_id) or the gross/net pricing switch, leaving those to the schema.

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 every parameter including the nested line-item fields is already documented, which sets the baseline at 3. The description reinforces two required inputs (payment_term_id source, at least one line item) but adds no syntax or constraint detail beyond the schema; notably it omits the gross/net pricing nuance and customer_id sourcing that the schema carries.

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 ('create a DRAFT outgoing invoice') and pins the resulting state (draft, not finalized or sent, no invoice number until completed in Papierkram). The 'WRITE:' prefix and 'create' verb distinguish it from the get_/list_/update_ siblings at a glance.

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 prerequisites: a payment term id sourced from papierkram_list_payment_terms and at least one line item, plus a follow-up path via papierkram_list_invoices to verify. It does not explicitly state when NOT to use it (e.g. correcting an existing invoice vs. creating a new one), so it falls just short of full alternative routing.

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