Создать возврат товаров поставщику

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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false) by disclosing that the document is left unposted, that posting reverses the receipt with specific entries (Дт 60 Кт 41/19), and that the settlement account derives from the contract settings and is visible in the preview. Missing only a note on duplicate-risk/operationId reuse, which lives in the schema rather than the description.

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 object being created, then constraints, then the posting alternative, then the workflow gate. It is telegraphic and dense but every clause carries operational meaning; a slightly more structured phrasing would read better than the semicolon chain.

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 10-parameter mutation with an output schema and safety annotations, the description covers what an agent most needs: unposted state, the posting follow-up, accounting effect, and the dry-run gate. Return-shape details are correctly omitted since an output schema exists.

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; the description still adds meaning by tying contractRef to the settlement-account resolution rule and by framing confirm as a preview-then-confirm gate. It does not explain other parameters (warehouse, organization, sumIncludesVat), so it stops short of a 5.

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 ("Создаёт документ «Возврат товаров поставщику»") plus the tabular section it fills ("Товары"). It also disambiguates from the closest sibling by naming post_document as the separate posting step and noting the counterparty is a supplier, which separates it from create_return_from_customer.

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 says the document is created НЕПРОВЕДЁННЫЙ and routes posting to post_document, so the agent knows the alternative and the condition selecting it. The dry-run/confirm protocol is stated as a mandatory flow rather than left to inference.

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