update_client

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

The only annotation is idempotentHint=true, so the description carries most of the burden. It usefully discloses patch semantics (omitted fields are presumably preserved) and the field combinations required for e-invoicing validity, which the annotation does not cover. However, it says nothing about what happens on a partially invalid payload, whether validation errors surface at write time, permission requirements, or what the call returns.

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 compact sentences: the patch rule is front-loaded, then the conditional e-invoicing prerequisites. Every clause does work; the only shortfall is that the e-invoicing clause is dense enough that an agent may need the schema to unpack address_*.

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 mutation tool with a nested free-form object, no output schema, and a third of parameters undocumented, the description covers purpose, patch semantics and one important field-validation rule. Gaps remain around the contents of `data`, error/rejection behavior, and confirmation of what a successful update returns.

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 33%, and the critical `data` parameter is an opaque object with additionalProperties: {} and no documentation. The description partially compensates by naming concrete keys that live inside it (tax_code, address_*, SDI code, certified_email), which is genuinely useful. It still does not enumerate the rest of the updatable client fields or explain the shape of address_*.

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 verb and resource are explicit ("Modifica un cliente"), and the added "passa solo i campi da cambiare" pins down that this is a partial update rather than a replace. It separates cleanly from create_client / delete_client / get_client by verb alone, though it never names those siblings.

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 a concrete usage rule (send only changed fields) and gives conditional prerequisites for electronic invoicing: either a VAT number or tax code, plus address_* fields, plus an SDI code or certified email (PEC). That is real when-to-use guidance, but there are no exclusions or pointers to alternatives, and nothing about ordering or how to correct a rejected payload.

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