prepara_modifica_prezzo_prodotto

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

With no annotations, the description carries the full burden and does well: it discloses that nothing is persisted ('senza salvare'), that it drives the browser rather than the DB, and that a human-visible screenshot gates the change. It leaves out what happens to a pending modification if neither confirm nor abort is called, and whether the operation is repeatable.

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?

Short and front-loaded: the action is in the first sentence and the safety rationale and next steps follow. Line breaks are a bit awkward and one clause ('così l'utente puo' controllare lo screenshot') is slightly redundant with the 'sensibile' framing, but almost nothing is wasted.

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 sensitive two-step mutation with no annotations and no output schema, the description covers the staging model and the required next call, which is the core need. It is silent on what the tool returns (a pending-modification handle? the screenshot?) that the follow-up tool presumably consumes, which matters for chaining correctness.

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 0%, so the description must compensate and it largely does not: 'nuovo_prezzo_regolare' is typed as a string with no indication of format (decimal point vs comma, currency, thousands separators), which is a realistic failure mode for a price field. 'prodotto_id' is only implied by the noun 'prodotto'; no hint on where to obtain a valid id.

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 ('Compila il nuovo prezzo regolare di un prodotto in wp-admin') and immediately scopes it as non-committal ('senza salvare'), which distinguishes it from applica_aggiornamento_prezzi and conferma_modifica_in_corso. An agent can identify exactly what this does 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?

Gives an explicit operating condition ('Operazione sensibile: usa il browser... così l'utente puo' controllare lo screenshot prima che la modifica diventi effettiva') and prescribes the mandatory follow-up branching ('Dopo questo tool chiama conferma_modifica_in_corso oppure annulla_modifica_in_corso'). The when-to-use and what-to-do-next are both spelled out with named siblings.

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