ozon_discount_prepare

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), so the bar is lower, and the description still adds real behavior: it fills the form without submitting and returns a preview plus a confirmation payload. It stops short of explaining what the confirmation actually is (token? identifier?), which is needed to chain into the confirm step.

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?

Two short sentences with the action verb front-loaded and zero filler. The negative constraint ('НЕ отправлять') is placed where it is most visible, and each sentence carries distinct information.

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 does cover what comes back (preview and confirmation), and annotations cover the safety profile. However, the required url input, the authentication requirement, and the nature of the returned confirmation are all unaddressed, which leaves gaps for correctly invoking and chaining the tool.

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 0%, so the description has to carry the parameter load. It partially does, naming 'цену/текст' which map to requestedPriceRub and message, but the required 'url' parameter is never mentioned, leaving a third of the inputs undocumented anywhere.

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 gives a specific verb and resource ('Подготовить запрос Хочу скидку') and immediately draws the critical line against the send/confirm phase by stating 'НЕ отправлять.' That boundary is exactly what separates it from confirm-style siblings such as ozon_action_confirm, so an agent can classify it 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?

Usage is implied rather than explicit: it says it prepares a form and does not send, which lets a reader infer the two-step prepare-then-confirm flow. It never states when to prefer it over a sibling, nor any prerequisites (authentication, a valid product URL, whether an existing pending request must be cleared first).

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