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

Annotations only cover the safety profile (read-only, non-destructive, closed-world); the description adds the operational traits that actually matter here: async/slow (Orders API ~1 call/minute), RUNNING is not zero and must be re-polled with retry_after_seconds, DONE payload shape, and a private signed TSV link valid 7 days that must never be published. It also discloses PII omission (no buyer name, address or email).

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 'READ-ONLY' then purpose, and virtually every sentence carries information an agent needs (trigger, column list, async protocol, link handling). The single dense paragraph is harder to scan than bullets would be, which is the only real deduction.

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?

There is no output schema, and the description compensates fully by describing what DONE returns (totals per type, type x marketplace x ship-to country x B2B x currency summary, data checks) and the download_url delivery mechanism. Permissions, timing, polling and scope-of-one-outpost are all covered.

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% so the baseline is 3, but the description genuinely adds meaning beyond the schema: the 400-day maximum span on start_date/end_date, the inclusive/UTC semantics, and the guidance to pick one outpost for account_id. It does not, however, clarify the refresh behavior beyond what the schema already says.

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 (export) plus the exact resource and granularity: one row per order item for sales (VENDITA), refunds (RIMBORSO), A-to-Z claims and chargebacks, with an enumerated column list and stated source (SP-API Finances + Orders). No sibling covers fiscal/VAT data, so it is unambiguous against every other tool in the list.

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?

Explicit trigger: 'Use when the user needs the VAT transactions / report transazioni IVA and the Amazon VAT Transactions Report (AVTR) is not available' names the alternative and the condition that selects this tool. It also sets the boundary ('Not a legal VAT return... compare with the AVTR before filing'), so when-not is covered too.

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