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

Annotations already declare readOnly/idempotent/closed-world, and the description adds real context beyond them: the link expires in 48 hours and the actual payment is performed by a human, not the agent. It does not say what happens when a check_id is invalid or an existing link is re-requested, which are the remaining behavioral gaps.

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 core action is front-loaded in the first sentence, followed by the human flow, the expiry limit, and the agent's exclusion — every sentence carries distinct information with no restatement of the name or schema.

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 still tells the agent the return value is a site link, plus its 48-hour lifetime. For a two-parameter tool that is nearly complete; only error/edge behavior is unstated.

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 only 50%, and the description compensates by explaining the provenance of the undocumented check_id ('из check_site'). sku is left to the schema enum, which already spells out fix vs fixpro, so nothing critical is missing.

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: returns a payment-page link built from a check_id plus a chosen SKU. It also anchors the tool to its sibling by saying check_id comes from check_site, so an agent can tell it apart from check_site and get_offer without opening any 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?

The human-payment flow ('человек открывает её... платит сам') makes the when-to-use condition clear, and 'Агент оплату не проводит' is an explicit when-not boundary for the agent itself. It stops short of naming get_offer as the place to fetch offer terms, so the routing is clear but not exhaustive.

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