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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false): it discloses that the draft is not booked, stays editable, reaches no recipient, needs no confirmation, copies recipient name and VAT zone from the customer, and requires a Cotlet API key with app access. This is exactly the behavioral context an agent needs for a mutation.

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 purpose and generally efficient, but 'The draft is not booked' is restated twice and the field list ('customer, date, currency, payment terms, layout') duplicates what the schema already enumerates. Minor redundancy keeps it from a 5.

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?

With no output schema, the description appropriately explains the return (draft number plus net, VAT and gross totals) and covers auth requirements and the non-committal nature of the operation. Nothing essential for correct invocation is missing.

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 already 100%, so the schema documents all six parameters. The description adds modest value, clarifying that lines accept either a product number or free text with quantity and unit price, but provides no further syntax beyond that. Baseline 3 is appropriate.

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) and resource (draft invoice) with scope ('for a customer with lines') and distinguishes itself from siblings like e-conomic_book_invoice and e-conomic_list_draft_invoices by emphasizing the draft, unbooked nature. An agent can tell it apart from booking/sending tools without opening the schema.

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?

Clearly signals the intended context -- a non-committed, editable draft that 'reaches no one and runs without asking first' -- which implicitly tells the agent when this is appropriate versus a booked/sent invoice. It stops short of explicitly naming the alternative book/send tools and the condition that selects them, so it doesn't reach a 5.

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