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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered structurally; the description reinforces the read-only nature ("No compra nada") and, more usefully, enumerates the payload contents (productos, envío, total, entrega de demo). It doesn't cover failure modes such as an invalid or expired token, which is the main remaining gap.

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?

Two tight sentences with no filler; the purpose and the returned contents come first, followed by the anti-pattern warning. Nothing here could be cut without losing information.

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 does the necessary work of listing what the call returns, which is exactly what an agent needs. It falls slightly short by not saying what happens when 'carrito' is omitted (the schema marks 0 required parameters) or when the token is invalid.

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% and the single parameter 'carrito' is documented as a token (c1.…), so the baseline is met. The description adds mild value by tying the token to both this call and the follow-up crear_pedido call, reinforcing the token's continuity across tools.

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?

Specific verb + resource ("Muestra el carrito") plus an explicit inventory of what is returned: productos, envío, total y la entrega de demo. It also distinguishes itself from crear_pedido in the same sentence, so an agent can separate viewing from ordering without opening a schema.

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?

States the negative case outright ("No compra nada") and routes the agent to the correct alternative ("para pedir usa crear_pedido"), including the handoff detail that the same 'carrito' token is reused. This is the explicit when/when-not/alternative pattern.

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