duplicate_document

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

With no annotations supplied, the description carries the full burden and does well: it discloses the side effects that matter most (the copy is not sent to SdI and not emailed), explains that deadlines shift by the original interval, and offers a dry-run preview path. It omits whether the copy lands as a draft, any permission/numbering prerequisites, and what is returned.

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 sentences, front-loaded with the identity of the operation and its preserved/regenerated fields, then the side-effect caveat, then the dry_run tip. The parenthetical "(come «Duplica», ma completo)" is a small waste but everything else earns its place.

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 6-parameter tool with a nested overrides object, no annotations and no output schema, the description covers the copy semantics and safety caveats well but leaves the override capability entirely undocumented and says nothing about the returned document or its initial state. An agent could call it correctly, but not exploit it fully.

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 67%, so the schema already documents date, number, company_id and the rich overrides template syntax. The description adds real meaning for date/number by explaining they are regenerated (new date, next free number) rather than copied, but it never mentions the large nested overrides object, which is the highest-complexity part of the schema.

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?

The description gives a specific verb and resource ("Copia un documento esistente") and enumerates exactly what is preserved (cliente, righe, bollo, metodo e conto di pagamento) versus what is regenerated (nuova data, numero successivo, scadenze spostate). It does not, however, distinguish itself from close siblings such as bulk_duplicate, transform_document or create_issued_document, so an agent must infer the boundary.

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?

There is one concrete usage instruction — use dry_run=true to preview before creating — which is genuinely actionable. But there is no guidance on when to choose this over bulk_duplicate, transform_document, or plain create_issued_document, and the 'when not to use' case is only implied by the no-SdI/no-email note.

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