Создать заявку на вывод (шаг 2)

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

There are no annotations, so the description has the full burden. It clearly states this is a money operation but that funds do not move yet (non‑destructive intermediate step). It discloses that the response contains credentialTokenId and that this is a necessary input for confirmation. It also notes the API limitation regarding card numbers, which is an important behavioral constraint. This is a well-transparent disclosure beyond any structured metadata.

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 description is dense but has no redundancy: it begins with the most critical truth ('money still doesn't leave'), then the preceding call, then the needed credential, then the SBP‑specific constraints, and finally the card limitation. Every clause contributes to the correct invocation; no filler words.

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?

Despite having 10 parameters, no output schema, and no annotations, the description fills the missing orchestration context: where identifiers come from, which fields are required per payment method, what the next step is, and which actions are impossible. The agent has enough to recommend and row the API call without consulting external docs.

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?

The input schema already has 100% description coverage, with each parameter described (e.g., 'orderId из расчёта комиссии', 'phone 11 цифр начиная с 7'). The description reinforces which parameters are relevant for SBP and crypto, but it does not add fundamentally new information beyond what the schema provides. Per the rule, a 100%‑coverage schema gives a baseline of 3.

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 uses a specific verb and resource ('Создаёт заявку на вывод') and immediately clarifies the step nature by adding 'деньги ещё не уходят' (money doesn't leave yet). It distinguishes this tool from the following confirmation step (wata_wallet_withdraw_confirm) by naming the credentialTokenId that will be returned, and from the commission tool by saying it is a prerequisite. The card limitation also makes the boundary of what the tool does unambiguous.

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?

Explicit when-to-use guidance is present: the first sentence instructs the agent to call wata_wallet_withdrawal_commission first, and that orderId/quoteId come from there. It also specifies branch-specific requirements for SBP (bankNumber from wata_wallet_banks, phone length/prefix) and tells the agent that withdrawal to a card through the API is impossible, therefore implying this tool is not for card withdrawals. This fully covers when to use and when not to use.

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