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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false) the description discloses the key behavioral fact that the plan is created as a modifiable draft and that no shipment starts ('il piano nasce come bozza modificabile, NON parte nessuna spedizione'), plus the two-step confirm_id write mechanism and the boundary that transport/labels are not covered in this version. This is substantive context the agent needs to set user expectations.

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 'ACTION' and the core purpose, then a cleanly numbered sequence. It is dense and somewhat long, but each block (purpose, flow, precondition, rollback) earns its place; only the flow enumeration is heavier than strictly necessary.

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 and a nested-object, multi-step mutation, the description fills the gap completely: it explains the draft outcome, the confirmation contract, the downstream steps, and where the process stops. An agent has everything needed to invoke it correctly and guide the user.

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 80%, so the schema already documents name, items, account_id, confirm_id and source_address fields. The description restates the required inputs (SKU, quantità, indirizzo) but adds no syntax, format, or constraint detail beyond the schema, so the baseline of 3 for high-coverage schemas applies.

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 names a specific verb and resource ('Crea un PIANO di spedizione FBA'), pins the resource to the exact API surface ('Send to Amazon', Fulfillment Inbound v2024-03-20), and specifies the inputs (SKU + quantità + indirizzo di origine). It also positions itself as PASSO 1 of a known flow, which distinguishes it from siblings like confirm_inbound_option and generate_inbound_options.

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 gives an explicit 6-step sequence showing exactly where this tool sits and which tool follows, states the precondition ('PRIMA di chiamare: mostra all'utente il riepilogo... e chiedi conferma esplicita'), and names the rollback alternative ('cancel_inbound_plan'). When/when-not guidance is fully covered.

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