Strumenti di calcolo dello Studio Notarile Chianese

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

Annotations already declare a safe, read-only, idempotent computation, so the description's job is to add context — and it does: it discloses the return content (amount paid via the notary on deed day, total, itemized entries, first-home comparison) and two important limits (no notary honorarium, full ownership only, not a formal quote).

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?

Front-loaded with the purpose, then inputs, then outputs, then exclusions; every clause carries information and the closing English sentence aids disambiguation. It is dense but not padded, though the enumerated tax list makes it longer than strictly necessary.

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 9-parameter, high-complexity tax calculator with an output schema and full annotation coverage, the description covers purpose, when to use it, required inputs and their conditions, output content, and explicit exclusions. Nothing needed to call it correctly is missing.

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% with richly documented enums, so the baseline is 3. The description goes slightly beyond by naming the conditional input dependency (price always, plus cadastral income when a person buys and the sale is VAT-exempt) and pointing to the visura as the source of rendita catastale.

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?

States a specific verb and resource (calculates Italian purchase taxes on a home or pertinenza) and enumerates the exact tax items covered (registro/IVA, ipotecaria, catastale, Archivio notarile, loan tax). It is readily distinguishable from siblings such as imposte_successione_donazione, usufrutto_nuda_proprieta or valore_catastale, which address different tax/valuation scenarios.

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?

Gives an explicit trigger: 'Si usa quando una persona chiede quante imposte pagherà comprando', and scopes it to private-vs-company sellers and with/without first-home relief. It also states a boundary (excludes notary fees, is not a quote), though it never names a sibling tool as an alternative for adjacent questions.

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

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.

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context: it returns shares as fractions and optionally in euros, and it explicitly excludes inheritance tax calculations. It does not, however, need to restate the read-only nature already covered by 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 front-loaded with the core purpose and usage, followed by required inputs, return format and exclusions. It is somewhat dense and includes a full English translation that repeats the Italian content, but for a complex legal calculation tool this redundancy is minor and the structure remains clear.

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 nine parameters, two enums, an output schema, and read-only annotations, the description is complete enough for an agent to select and invoke the tool correctly. It covers purpose, usage, required inputs, conditional parameter relevance, return format, and scope limitations including the relevant sibling tool.

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 all parameters are already documented in the input schema. The description adds conditional relevance by noting that spouse and number of children are needed, while parents and siblings matter only when there are no children or descendants. This goes beyond the schema by clarifying which inputs drive the calculation in different scenarios.

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 calculation task: under Italian law, it determines who inherits, each heir's share when there is no will, and the forced share reserved to spouse, children and parents. It clearly distinguishes itself from imposte_successione_donazione by explicitly excluding inheritance taxes.

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 states when to use the tool (when asked who inherits, how much each receives, or how much can be disposed of by will) and names the alternative for tax calculations. It also sets scope boundaries by referring grandparents, other relatives, renunciations and indignity cases to a separate study.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower; the description still adds real value by disclosing the return contents (age at the act date, bracket, both percentages, both euro values) and the edge-case warning when a nearby birthday shifts the bracket. It does not need auth or rate-limit notes for a pure calculator.

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?

Front-loads the core function, then usage, inputs, outputs and exclusions in a logical order, with a compact English gloss appended. Slightly long, but each sentence carries distinct information and nothing is padded.

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 an output schema already exists, return values need not be explained, yet the description still covers function, usage conditions, inputs, outputs and edge cases (birthday near the act date, multiple usufructuaries). Nothing an agent needs to invoke it correctly is missing.

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 dataAtto, dateDiNascita and valorePienaProprieta, including the 'counts the youngest' rule. The description only restates which inputs are needed, adding no syntax or format detail 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?

States a precise verb and resource: it splits a property's full value into life usufruct and bare ownership using Italy's statutory age-based percentages. It also demarcates itself from the sibling tax tools by explicitly saying it does not compute taxes or market estimates.

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?

Names the concrete situation (someone sells or gifts a house while retaining usufruct, or buys bare ownership) and states the required inputs. It also gives explicit negative boundaries: no fixed-term usufruct, no market valuation, no tax computation, which cleanly routes the agent away from sibling tools.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's added value is telling the agent what comes back (valore in euro plus the conto) and, importantly, what it is NOT (not market value, not IMU value) and where it declines to apply. That boundary disclosure is genuinely useful; it stops short of richer detail like rounding or rate assumptions.

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?

Dense but front-loaded: purpose first, then usage, then what it returns and what it excludes, with an English gloss at the end. Every sentence earns its place, though the text is on the long side and the bilingual repetition adds length.

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?

An output schema exists, so return-value detail is not required in the description, yet it still summarizes the output (euro value plus the calculation) and enumerates the non-applicable cases. Combined with the rich schema and annotations, an agent has everything needed to invoke it 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% and each parameter has a thorough description with enum semantics, so the schema carries the burden. The description adds only the note that casa and pertinenze have separate rendite and that la rendita is found in the visura catastale, which the schema largely already states. Baseline 3 is appropriate.

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?

Starts with a specific verb+resource: calcola il valore catastale di una casa o pertinenza dalla rendita catastale, and frames what it is (tax base under prezzo-valore). It explicitly names siblings it is not (imposte_acquisto_casa, imposte_successione_donazione), so an agent can route without opening schemas.

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?

States the trigger clearly (the person knows the rendita and asks for the cadastral value), covers a second use case (deriving cadastral value for immobili that imposte_successione_donazione requests), and gives explicit exclusions: uffici, negozi, capannoni, terreni, company purchases. It also routes the acquisition-tax question to imposte_acquisto_casa.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value: it discloses the itemized return, the non-monetary differences under legge 182/2025, that defaults apply for missing data, and the notary-fee exclusion.

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 core purpose is front-loaded and each sentence conveys useful scope or constraint. The verbatim English restatement is somewhat redundant for an agent, but the Italian body is efficient and well-ordered.

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 8 documented parameters, an output schema, and rich annotations, the description fills the remaining gaps: what is computed, physical vs non-physical differences, legal backdrop, exclusions, and default behavior. Nothing needed to invoke it correctly is missing.

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 parameters are fully documented structurally; the baseline is 3. The description adds only mild extra context (the rendita catastale comes from the visura, the required inputs, the parentela default), not enough to exceed the baseline.

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?

States a precise verb+resource: it compares the taxes of a sale vs a gift of the same home to a relative in Italy, including the usufruct / bare-ownership case. This is clearly distinguishable from siblings like imposte_successione_donazione or quote_ereditarie without opening the 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?

Explicitly gives the triggering situation (someone undecided between selling and gifting, asking what each route costs) and states a boundary: it does not include the notary fee and is not a quote. It does not name a specific alternative sibling to use instead, 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.