Создать счёт-фактуру выданный

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

Annotations only declare write/non-destructive/open-world; the description adds materially more: the created document is unposted, requisites are inherited rather than supplied, and the operation follows a dry-run/confirm flow. Permissions, numbering behavior, and duplicate handling are not covered, keeping it below a 5.

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?

Four short sentences, front-loaded with the create action and basis, then the unposted state, then the confirm protocol. No filler; the only mild inefficiency is that 'dry-run/confirm' at the end duplicates what the confirm parameter description already covers in detail.

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 7-parameter mutation tool with full schema coverage, an output schema, and populated annotations, the description supplies the essential missing pieces: the mandatory base document, the inherited-field model, and the post-creation step. An agent has enough to call it correctly in a dry-run-first workflow.

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 by stating that organization, counterparty, contract, amounts, and VAT are inherited from the base document — explaining why no such parameters exist and reinforcing that baseDocumentRef is the controlling input.

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 names a specific verb and resource ('Создаёт «Счёт-фактура выданный»') and states the creating basis (реализация or another shipment document), which lets an agent distinguish it from generic invoice-creation siblings. It does not explicitly contrast itself with write.sales.create_invoice or write.purchase.create_received_invoice, so differentiation relies partly on the tool name.

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?

It gives clear when-to-use context (must be based on a shipment/realization document) and an explicit next step ('НЕПРОВЕДЁННЫЙ; провести — post_document'), plus the dry-run/confirm protocol. It stops short of naming exclusion cases, e.g. when to use create_invoice instead of an issued invoice.

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