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

Annotations only supply destructiveHint=true, so the description carries most of the burden and delivers: created unpaid (no payment recorded), nothing sent, no attachments, and the non-idempotent warning that a second call records a second expense. This is exactly the behavioral detail an agent needs before writing, and it is consistent with destructiveHint.

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 'WRITE:' marker followed by terse, information-dense sentences; the endpoint reference closes it out. No filler, and each clause conveys a distinct constraint or effect.

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?

Given sparse annotations and no output schema, the description covers what an agent must know: write semantics, unpaid/unsent result, attachment limitation, idempotency behavior, and the endpoint. Nothing critical to invoking it correctly 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 coverage is 100%, so parameter documentation is already handled and baseline would be 3. The description adds a modeling constraint beyond the schema: only a single total amount plus one VAT rate is accepted, i.e. no line-item breakdown, which affects how amount/vat should be populated.

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 ('records a received document (expense)') plus an example ('a supplier invoice or a bill'), which cleanly separates it from the sibling superfaktura_create_invoice (issued documents). The 'ONE total amount and VAT rate' phrasing also signals the modeling constraint up front.

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?

The description gives clear context for when this applies (received supplier documents, created unpaid, no attachments sent), which is enough to route an agent correctly. It stops short of naming alternatives or exclusions explicitly (e.g. 'for issued invoices use create_invoice'), so it is strong but not exhaustive.

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