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

Annotations already declare readOnly=false, destructive=false, idempotent=false, openWorld=false. The description adds real value beyond them by disclosing that no document number is assigned yet and that amounts are net EUR, but it says nothing about permissions, what the draft blocks or enables (send, PDF, e-invoice XML), or whether repeated calls duplicate records despite idempotentHint=false.

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?

Two sentences, zero filler, with the draft/no-number constraint and the unit-of-currency rule front-loaded before the recipient guidance. Nothing repeats the schema.

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 25-parameter creation tool with no output schema, the essentials of what a draft is and how to identify the recipient are present, but the agent is left guessing about the returned identifier, whether a draft is editable, and how the tax/e-invoice parameters interact with the draft state.

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?

With 25 parameters at only 32% schema description coverage, the description would need to carry a lot; it compensates for the highest-stakes decisions only — type (quote vs invoice), that amounts are net EUR, and the customer_id vs customer_name/address alternative. The remaining ~17 undocumented fields (payment terms, e_invoice_profile, service dates, buyer_reference) get no help in the description either.

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 ("Angebot oder Rechnung als Entwurf anlegen") plus a defining qualifier ("noch ohne Nummer") that separates a draft from a finalized document. An agent can distinguish this from finalize_document or update_document, though neither sibling is named explicitly.

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?

Implies the when: use this to create a new draft rather than to edit or finalize one, and points at list_customers as the source of customer_id. But it never states that after creation you must call finalize_document, nor when to prefer update_document over re-creating, so the workflow context is only inferred.

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