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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds valuable context beyond those annotations: it is deterministic, free, requires no login, returns obligations for both parties with applicable legal references, and treats non-EU countries as an explicit error rather than a supported branch. No contradiction with 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 dense but well-organized: purpose and result first, then the three confusing cases with legal references, then operational characteristics. Every clause earns its place and no information is redundant with the structured schema.

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?

With no output schema, the description compensates by stating what is returned: the VAT amount the buyer must self-assess and the obligations of both parties with the applicable rule. It also clarifies the main edge case (non-EU supplier). It stops short of describing the exact output structure, but is sufficient for an agent to select and invoke the tool correctly.

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 all parameters already have descriptions. The description adds meaningful legal nuance to 'paese_cedente' by explaining how its values map to the three reverse-charge scenarios and to the error case, which helps the agent select valid inputs correctly.

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 uses a specific verb ('Calcola') and a precise resource (IVA dovuta in regime di inversione contabile), and clearly differentiates the tool from generic VAT calculators by naming the three reverse-charge cases it handles. Even without naming siblings, the scope is unambiguous and specific to the tool's domain.

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 clearly states when to use the tool: for reverse charge calculations involving EU non-IT suppliers, Italian suppliers in specific sectors, and it explicitly says non-EU suppliers are an error case. It provides clear context and an explicit exclusion, though it doesn't name alternative sibling tools like calc_iva or calc_split_payment.

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