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

Annotations already declare readOnlyHint/idempotentHint so the safety profile is covered, and the description adds real behavioral context beyond them: it discloses what is returned (total, per-beneficiary amounts, line items) and a legal-state caveat (post legge 182/2025 donation resale/mortgage rules), plus the exclusion of notary fees. It stops short of discussing precision or edge-case limits.

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 purpose and usage condition are front-loaded, and every sentence carries substantive content (scope, inputs, outputs, legal note, exclusion). It is somewhat long, and the appended English translation duplicates Italian content rather than adding information.

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 an 8-parameter tool with enums, a rich schema, an output schema and read-only annotations, the description covers what it computes, when to use it, what it requires, roughly what it returns, and an explicit exclusion. It is essentially complete, with only the sibling-routing dimension left implicit.

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%, so the schema already documents every parameter including enums and the catastal-vs-market value distinction. The description reinforces which inputs are mandatory (recipients with kinship, the values) and points to valore_catastale for deriving rendita, but adds little 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 states a specific verb+resource (calculates Italian inheritance/gift tax) and enumerates the exact components covered: franchigie by kinship, ipotecaria/catastale on real estate, bollo and other items, plus a comparison mode between inheritance and gift. This lets an agent distinguish it from imposte_acquisto_casa or vendita_o_donazione without opening a schema.

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?

It gives an explicit trigger ('Si usa quando qualcuno chiede quanto si paga per un'eredità o per una donazione...') and a negative scoping note ('Non comprende l'onorario del notaio: non è un preventivo'). What it lacks is explicit routing against siblings like vendita_o_donazione or quote_ereditarie, though it does point to valore_catastale as a prerequisite helper.

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