lookup

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

readOnlyHint=true already tells the agent this is a safe read, so the description is not required to carry the safety burden. It adds the useful behavioral detail that the payload consists of id-bearing reference records intended for reuse elsewhere. It says nothing about company scoping of results, result size, or whether values are cached/filtered per company, which would matter for an agent choosing between repeated calls.

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?

It is a single compact sentence with no filler, and the enumeration maps one-to-one onto the required 'kind' enum, which makes it scannable. It reads as a flat noun list without a leading verb, which slightly weakens front-loading but wastes no words.

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 3-parameter read-only tool with no output schema, the description should at least signal the shape of what comes back (records with id and label) and how 'kind' plus 'context' interact. It hints at ids but never describes the response, and the company-scoping behavior of the default company_id is left entirely to the schema description.

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 67%, so the schema already documents the two optional parameters (context is restricted to product_categories, company_id defaults to FIC_COMPANY_ID or the token's sole company). The description mainly restates the enum values of 'kind' in Italian prose and adds the one semantic note that VAT type ids are the ones to use in rows. That is some added meaning, but it does not explain the product_categories/context interplay or the company_id fallback, so it does not clearly exceed the schema.

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 identifies the resource concretely: it is a reference/support-table reader and it enumerates exactly which tables (VAT rates, payment methods, payment accounts, revenue/cost centers, categories, templates, currencies, languages, countries, measures, DDT causals). It lacks a verb and, more importantly, never distinguishes itself from siblings like list_vat_types, list_payment_methods and list_payment_accounts, which appear to return the same data, so an agent still has to guess which one to call.

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?

Usage is only implied. The parenthetical '(con id da usare nelle righe)' hints that the returned ids are meant to be used when composing document line items, which is a genuinely useful pointer. However there is no explicit when-to-use, no when-not-to-use, and no mention of the overlapping list_* siblings, so routing is left to inference.

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