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

The "solo lectura" claim merely restates readOnlyHint=true, but the description genuinely adds the login/authentication requirement and the constraint that new addresses can only be created via the web, neither of which appears in the annotations. It does not disclose caching, rate limits, or whether last-order data can be stale.

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?

A single dense sentence with the payload enumeration front-loaded, followed by two short constraint sentences. Everything earns its place, though the payload list is packed into one long clause that could be broken up for scannability.

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 usefully enumerates the returned data shape (addresses as id + city/postal label, stores, shipping methods, reusable last order), and it covers read-only status, auth prerequisite and address-creation limitation. It omits how the country parameter changes results and gives no guidance on calling order relative to prepare_order.

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 100%, so the sole 'country' parameter already documents site selection, language, prices and links. The description does not reference the country parameter at all, so it adds nothing beyond the schema – baseline 3 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?

States precisely what the tool returns – saved addresses (id + short label), pickup stores, shipping methods and last-order defaults – and ties it to its consumer, prepare_order, which distinguishes it from prepare_order and prepared_order_status. However, it never states the action verb itself ("returns/retrieves"), so the function is inferred from the enumerated payload rather than declared.

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?

The framing "lo que hace falta para preparar un pedido con prepare_order" clearly positions this as the step preceding prepare_order, and it adds a real exclusion/limitation ("una dirección nueva solo se añade desde la web") plus a prerequisite (logged-in customer). It stops short of explicitly naming siblings to use instead in other situations (my_orders, list_stores).

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