Создать договор

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the mutation profile is known from structured data. The description still adds real behavior: preview by default, default number 'б/н' and today's date, and idempotent retry via operationId. However, the operationId/confirm mechanics are also documented in the schema, so the incremental disclosure over structured fields is modest.

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?

It is a single dense paragraph with the critical constraint ('kind' must be asked) and the dry-run default front-loaded, so nothing important is buried. Every sentence carries information, though the block could be split for easier scanning of the confirmation workflow.

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 13-parameter mutation tool with a full schema, annotations and an output schema, the description covers the risky parts: mandatory user-confirmed kind, preview-first workflow, defaults and idempotent retry. The remaining parameter detail (currency, priceType, database resolution) is left to the schema, which is acceptable given 100% coverage.

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 100%, so the baseline is 3 and the description would need to add meaning beyond the schema to score higher. It restates the kind constraint, the confirm/dry-run semantics and the defaults for number and date, all of which are already in the schema; the only added framing is grouping the optional head/signatory fields. Baseline 3 applies.

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 opens with a specific verb and resource ('Заводит договор контрагента') and immediately scopes it as a subordinate catalog whose owner is the counterparty. That is precise enough for an agent to know this creates a contract, not a counterparty. It does not explicitly name or contrast a sibling tool, which keeps it short of a 5.

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 states the key precondition explicitly: 'вид договора (kind) обязателен и его НЕЛЬЗЯ выбирать самостоятельно — уточните у пользователя', with the reason given (one counterparty can be both buyer and supplier). It also spells out the default dry-run path and the confirm=true path, including showing the preview first and obtaining consent. This is exactly the when/when-not guidance the dimension rewards.

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