Создать расходный кассовый ордер (РКО)

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

Annotations already declare readOnly=false, destructive=false and openWorld=true, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the created document is left unposted, posting requires a separate call, and the preview/confirm cycle with operationId prevents duplicates. Much of the dry-run detail, however, is duplicated from the confirm parameter's schema text rather than newly contributed.

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?

Front-loaded with the identity and the unposted-state caveat, then the mandatory field, then the contract nuance. The telegraphic, fragment-heavy style ('НЕПРОВЕДЁННЫЙ; провести — post_document') is dense but efficient; nothing is wasted, though the 'dry-run/confirm' tail is a redundant pointer to the confirm schema text.

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 13 parameters, an output schema, and full schema descriptions, the description covers the things structured fields cannot: mutation semantics, the unposted state, the posting sibling, and the mandatory operation type. It leaves the cash/contract selection prerequisites (which refs are required for which operationKind) and permission/auth expectations implicit.

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 100%, so the baseline is 3, but the description adds real meaning: it enumerates valid operationKind values ('ОплатаПоставщику', 'ВыдачаПодотчетномуЛицу', etc.) that the schema only says 'не угадывать' for, and explains the contract settlement breakdown logic behind contractRef/counterpartyRef. It still doesn't explain how the 'сумма взаиморасчётов' maps onto a concrete parameter.

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?

Names a specific verb and a specific 1C document type (Расходный кассовый ордер — cash disbursement), and clarifies the direction of money flow ('выдача наличных из кассы'), which implicitly separates it from the sibling create_cash_receipt. It also states the resulting document state ('НЕПРОВЕДЁННЫЙ') and points at post_document for the follow-up step.

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?

Explicitly routes the agent to post_document for posting and mandates the dry-run/confirm workflow, plus warns that operationKind is mandatory and must not be guessed. It does not, however, contrast this tool with the nearby alternatives (create_payment, create_payout_order, create_bank_writeoff), so the choice between cash vs bank disbursement is left to inference from the title.

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