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

Annotations already flag destructiveHint=true, but the description adds much more: approve=true applies new items, false leaves the order unchanged, and cancelOrder=true cancels the order. The expiresAt behavior and the auto-approval rule for reduction-only adjustments are behavioral facts unobtainable from the schema or annotations.

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 the action, then the prerequisite display step, then the outcome semantics, then expiry. Every sentence carries load, though the expiry sentence is dense and packs two distinct rules together, slightly reducing scanability.

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 destructive, non-idempotent mutation with no output schema, the description covers decision semantics, cancellation side effect, and the consequences of not responding in time. An agent has everything needed to call it correctly and safely.

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 baseline is 3, but the description adds real meaning: it explains the approve/cancelOrder interaction ('false mantém o pedido como estava, ou cancela com cancelOrder true') and that approve=true applies the new items. cartId is left to the schema, which already documents it as coming from create_cart.

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 ('Responde... ao ajuste') and resource (the store's proposed order adjustment), then enumerates the exact adjustment types it covers (missing item, similar-item swap, quantity, price). This clearly separates it from siblings like get_cart (which merely reads order.adjustment) and respond_to_quote.

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 prescribes the prerequisite workflow explicitly: first show the consumer order.adjustment from get_cart (with the change types and totalBefore/totalAfter) and only submit the consumer's actual decision. It also states the no-response policy (reduction-only adjustments auto-apply; others expire and the store decides), leaving no ambiguity about when and how to call it.

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