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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered structurally. The description adds genuine behavioral scope limits beyond that (top-10 shareholders by ownership share, cashflow only with a 2-year history, ATECO history only since 2022), but says nothing about auth/prerequisite steps, latency, cost, or behaviour when a VAT is unknown.

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 is front-loaded in the first sentence and the invocation guidance is placed at the end where it addresses the input. The bulleted data catalog is long, but each line documents a distinct returned field family the agent would otherwise not know about, since there is no output 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 correctly compensates by enumerating the returned data in unusual detail, and annotations cover the safety profile. The remaining gap is operational context – how to authenticate, what happens on a not-found VAT, and how it differs from the advanced/start siblings – which is not strictly required to call the tool successfully.

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 carry the parameter burden, and it only restates the arg label: it accepts a 'VAT number or Tax Code of an Italian company'. No format, length, country-prefix or validation detail is added. For a single required parameter with an explicit either/or hint, a 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?

The first sentence gives a specific verb and resource ('Returns the complete and detailed profile of an Italian company') and the following bullets enumerate exactly what is retrieved, so an agent knows the payload is far richer than the search/start variants. It does not, however, distinguish itself from siblings like get_company_IT_advanced or get_company_IT_start, so sibling disambiguation is only partial.

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?

There is one explicit routing hint – 'Use get_company_IT_search to obtain VAT' – which tells the agent how to obtain the required input. But there is no guidance on when to prefer this tool over get_company_IT_advanced, get_company_IT_start, or the docuengine/visura siblings, so usage is only implied for the main decision.

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