beel_patch_invoice

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

Annotations carry readOnlyHint=false, destructiveHint=false, idempotentHint=true, so the description is not required to restate those. It adds genuine behavioral context beyond them: PATCH partial-update semantics, the draft-only restriction, and the subtle series_id disclosure ('Changing series_id never moves the invoice to another NIF: a series of another company is not visible from here'). No contradiction with annotations — description's 'updates' aligns with readOnlyHint=false. Minor gap: no mention of response or VeriFactu side effects, but the bar is lowered by existing annotations.

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 compact and front-loaded: the first sentence states the core partial-update semantics, followed by the draft-only constraint, the series_id caveat, the endpoint, and pointers to guardrails/docs. Every sentence earns its place. The emoji-warning list is slightly stylistically noisy but functional and informative rather than padding.

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 complex fiscal tool with an enormous inline schema (tax rules, VeriFactu, exemption sentinels, equivalence surcharges) and no output schema, the description provides strong orientation: partial semantics, draft-only scope, the series_id NIF edge case, the endpoint, and explicit pointers to beel://guardrails/invoice-state-machine and beel_docs_search for exhaustive rules. It wisely delegates the heavy detail to the schema and docs. Missing only a response-format note, which is minor given the delegation strategy.

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 67% (company_id and invoice_id are well documented inline, with a rich note on company_id as sole NIF context). The description adds value specifically for series_id, explaining it never reassigns to another NIF's series — semantics not present in the schema's series_id entry. The body parameter carries exhaustive inline documentation in the schema, so the description correctly leaves it to the schema. Genuine added value for the one parameter that needed it.

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 with precise semantics: 'Updates only the fields present in the body, leaving every other field of the invoice as it is.' This clearly identifies a partial PATCH operation on a draft invoice and distinguishes it from a full replace/update. Sibling differentiation is implicit via the 'Only a draft invoice can be modified' constraint and the surrounding tool names (create_invoice, issue_invoice, void_invoice), but no sibling is named explicitly, so it stops short of a 5.

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 when-to-use context: 'Only a draft invoice can be modified: an issued one is amended with a corrective invoice or voided.' This both scopes the tool and points to the alternative paths (corrective/void) for non-draft invoices. It also routes to beel://guardrails/invoice-state-machine and beel_docs_search for exhaustive rules. However, it does not explicitly name alternative tools by name (e.g., use beel_create_invoice to create a draft first), so guidance is context-rich but not fully explicit.

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