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

Annotations only declare readOnly=false, destructive=false, idempotent=false; the description adds what matters: the link is valid 24h and appears only in this response, an all-or-nothing failure mode ('se algum item não puder entrar, nada é criado'), FROM pricing yields an estimate, and payment is settled with the store outside the platform. It also flags that confirmation requires the consumer's WhatsApp number on the confirmation page.

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?

Key constraint and purpose are front-loaded, but the body is one very long paragraph that packs fulfillment variants, rental, visit, coupon, and phone instructions without breaks. It earns most of its content, yet the density makes scanning hard for an agent deciding which branch applies.

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 13 parameters and no output schema, the description still covers the return payload (confirmUrl, discount, couponCode, expectedOn, per-item failure reasons) and the domain rules per fulfillment type. Nothing an agent needs to call this correctly for products, services, bookings, rentals, or visits is missing.

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 goes beyond it: it explains what each fulfillment value means operationally (pickup vs delivery vs shipping vs in_store vs at_customer vs booking vs digital), the minSelect-1 rule for options, the need to repeat an item for different choices, and when checkIn/checkOut/guests/startDate/endDate apply. A few params (note, externalReference, soldByWeight quantity) are left to the schema.

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?

Opens with a specific verb+resource ('Monta um carrinho numa loja') and names the output ('devolve confirmUrl, o link que o CONSUMIDOR abre'), which distinguishes it cleanly from get_cart (retrieval) and reorder. An agent knows exactly what is produced without opening the 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?

Explicit routing: use productId from search_products, storeId from get_offers, check quote_delivery before shipping, check_availability for slots, request_quote for ON_REQUEST items, get_promotions for coupon codes. It also states exclusions (products with receita don't enter, one cart per store) and prohibitions (never say the purchase was made, don't ask for the phone in chat).

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