beel_create_invoice_derivation

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

Beyond the minimal annotations (readOnlyHint false, destructiveHint false), the description discloses important behavioral details: the source invoice is not modified, specific fields are reset, and series validation may fail with a specific error (422 SERIES_INCOMPATIBLE_DOC_TYPE). It also highlights fiscal guardrails and points to documentation for edge cases. This is rich behavioral context that goes well beyond what annotations provide.

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?

The description is longer than typical but well-structured: a clear opening sentence states the purpose, followed by copy/reset details, a note on series validation, the endpoint, a guardrail warning, and a pointer to docs. Each section earns its place, though some redundancy exists (e.g., repeating the mode and source behavior). It is effectively front-loaded and easy to scan, but could be slightly tightened.

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 the complexity of the operation, the absence of an output schema, and the detailed input schema, the description covers essential aspects: what gets copied and reset, the source not being modified, series validation and error handling, and where to find exhaustive rules. It does not explicitly state the return value, but that is consistent with the lack of an output schema and is not required for correct invocation. The references to docs and guardrails fill remaining gaps, making it sufficiently complete.

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 schema description coverage at 67% (two of three parameters documented in detail), the description compensates by explaining the conceptual role of parameters: from_invoice_id names the source, mode DUPLICATE copies it, and series_id defaults to the source's. It clarifies the intent that this call does not describe an invoice but names one, which adds meaning beyond the schema's property descriptions. However, it does not dwell on idempotency_key semantics, which are already present in the schema, so the added value is strong but not exhaustive.

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 states a specific verb and resource: 'Creates a draft invoice derived from an existing invoice'. It details exactly what is copied and reset (recipient, lines, payment method, series, observations, number, status, dates, VeriFactu data, PDF) and distinguishes itself from beel_create_invoice by explaining this call names a source invoice rather than describing one, and from beel_convert_proforma_to_invoice by noting it is not a derivation mode. This makes the purpose unambiguous and clearly separates it from siblings.

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 provides clear context for when to use this tool: it is for duplicating an existing invoice, explicitly contrasting with the standard create request ('not a variant of the create request on purpose') and mentioning that turning a proforma into an invoice is a different operation. It also advises consulting fiscal guardrails and points to beel_docs_search for exhaustive rules. However, it does not explicitly enumerate all sibling alternatives in a structured when/when-not form, so it falls just short of a 5.

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