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

Annotations already mark the tool as non-read-only, non-idempotent, and non-destructive. The description adds genuinely new behavioral context: it guarantees no payment is taken, requires OAuth, and discloses the return payload (cart_id, contents, site link) in the absence of an output schema. This materially helps an agent set accurate expectations with the user. There is no contradiction with the 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?

Three short sentences with the core action first, followed by return values and then caveats. Every sentence earns its place; there is no repeated schema content, filler, or redundancy.

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 moderate-complexity mutation with no output schema, the description covers the essentials: input format, return values, auth requirement, and the non-payment guarantee. Gaps remain around edge-case behavior (invalid variants, stock validation, whether repeated calls produce duplicates), which an agent might need when handling failures, but nothing required to make a correct first call 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 description coverage is only 50% (cart_id is documented, items is not), and the description compensates in prose by framing the array as 'variant_id + количество' (variant_id + quantity), adding meaning to the otherwise undocumented parameter. Quantity constraints (min 1, default 1) and the merge behavior of cart_id still come only from the schema, and the description doesn't clarify what variant_id references or how quantities accumulate in an existing 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 leads with a specific verb+resource: 'Собрать корзину' (build a cart) from a list of variant IDs and quantities, which precisely captures the operation. The clause 'Ничего не оплачивает' (pays for nothing) implicitly separates it from the payment/order sibling create_invoice_order. However, it never names or explicitly contrasts an alternative sibling, so differentiation from reorder, select_actuator, or suggest_accessories_for_cart is left to inference.

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?

The OAuth prerequisite and the explicit 'Ничего не оплачивает' caveat imply this is the pre-checkout assembly step, distinct from invoice/order creation. But there is no statement of when to choose this over create_invoice_order, reorder, or cart-adjacent tools, and no explicit exclusion criteria. Guidance is implied at best through the payment caveat.

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