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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the description's added value is the workflow context: the cart_url opens puhy.cz in the user's browser where the user completes checkout and payment, and successive cart_urls add to the same cart. That is meaningful context not present in the annotations. The tension between readOnlyHint=true and 'adds its items to the same cart' is real but plausibly browser-side rather than a server mutation, so it is a caveat rather than a contradiction.

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?

Three sentences, front-loaded with the returned payload, then the cart_url workflow, then the usage fit and limit. No filler, though the long run-on enumeration in sentence one is dense and could be split for 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?

With no output schema, the description responsibly enumerates return fields, and it adds the 50-line limit, the cart accumulation rule, and where payment happens. What is missing is partial-availability behavior (e.g., whether unavailable items still appear) and how the goods total and shipping options relate across the 50-line cap.

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 0%, so the description must carry the burden, and it partly does: "list of items with quantities" maps to the items array and "up to 50 lines per call" explains the maxItems cap. It says nothing about product_id format/validity or what happens to lines whose requested quantity exceeds stock, leaving the nested fields documented only by their names.

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 opens with a specific verb and resource ("Check a list of items with quantities") and enumerates exactly what comes back: orderable quantity, price, stock, delivery time, goods total, shipping options, and cart_url. It implicitly separates itself from get_product and search_products by working on a multi-line list, but it never names those siblings explicitly.

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?

"Suited to BOMs / parts lists: up to 50 lines per call" gives a clear usage context, and the note that each cart_url accumulates into the same cart is useful. However, there is no explicit when-not guidance and no routing to get_product for a single item or get_shipping_and_payment for shipping-only lookups, so the agent must infer the boundaries.

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