preview_totals

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

readOnlyHint=true already declares the safety profile, and 'senza crearlo' reinforces that no document is persisted, which is a useful confirmation of the dry-run nature. Beyond that, the description says nothing about error behavior, whether totals can differ from a later real creation, or quota/auth constraints, so it adds only modest context over the 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?

Two tight sentences: the computation and its non-mutating nature come first, then the usage cue. Every phrase carries information, including the enumerated output fields, with no filler.

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 read-only preview tool with no output schema, the description usefully lists the returned totals, which compensates well for the missing return spec. What remains unstated is how the nested IssuedDocument payload is interpreted or what happens on invalid data, minor gaps given full schema coverage.

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 100%, with 'data' documented as an IssuedDocument object 'come per create_issued_document' and company_id's defaulting behavior spelled out in the schema. The description only implies that 'data' is the document payload, adding no field-level meaning beyond the schema, so the baseline 3 applies.

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 ('Calcola ... i totali di un documento') and enumerates exactly which totals are produced (imponibile, rivalsa, IVA, ritenute, bollo, totale, somma delle rate). The clause 'senza crearlo' implicitly separates it from create_issued_document without naming that sibling outright, so differentiation is clear but not explicit.

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?

'Usalo per controllare una fattura prima di emetterla' gives a concrete moment to use the tool and implies the boundary versus actually issuing the document. It stops short of naming an alternative or stating exclusions, so it lands at clear context rather than full when/when-not guidance.

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