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

Annotations only declare the generic write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds substantive behavior the schema cannot express — no payment or order is committed, checkout happens on shop.nevini.wine after the customer opens checkout_url, and a legal age gate applies with possible ID check on delivery. This is exactly the kind of consequence-of-calling context the score rewards.

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?

The operational facts are front-loaded, but the legal block is repetitive: 'No order is placed' is restated as 'The order is only placed once the customer opens the checkout,' and the buyer_is_18_or_older instruction duplicates the schema's own description verbatim in intent. Roughly a third of the text could be compressed without losing meaning.

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?

Given an output schema exists, the description need not explain return values, yet it still names the key ones. It covers prerequisites (age confirmation), variant_id sourcing, language default, and the fact that no payment occurs — everything an agent needs to decide to call it and to set preconditions correctly.

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 schema already documents items, quantity range, variant_id source, language default, and the buyer_is_18_or_older confirmation rule. The description reinforces the variant_id provenance and the age-confirmation precondition but adds no syntax or format detail beyond what the schema states.

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 a specific verb and resource ('Creates a new Shopify cart') and immediately names the return payload (cart_id, items with live prices, subtotal, checkout_url). The word 'new' plus the variant-sourcing hint distinguishes it from the sibling add_to_cart, which operates on an existing cart.

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?

Explicitly routes the agent to search_wines or get_wine to obtain a variant_id, and clarifies the boundary of the operation: 'No order is placed and no payment is taken here; checkout_url opens the checkout.' It stops short of saying what to do if a cart already exists (use add_to_cart instead), which is the one contextual routing gap.

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