Создать номенклатуру

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

It adds behavior that the annotations do not cover: a default dry-run mode, a consent gate before writing, and the fact that the write goes to the production database ('боевая база'). Together with the annotations, which say readOnlyHint=false and destructiveHint=false, this fills the gap for a mutating tool.

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 one compact paragraph that leads with the dry-run warning, the most important information for an agent, and then covers the optional fields. Each sentence carries useful information, though the dry-run instruction could be tightened.

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?

Because an output schema exists and the input schema has 100% description coverage, the definition does not need to cover the return values. It covers the main behavioral risks: preview, consent and production write. Only the database and operationId parameters are left entirely to the schema.

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 schema already explains name, folder, article, confirm, database, fullName, isService and operationId. The description mentions folder and isService but adds no meaning beyond what the schema fields already state, so the baseline of 3 is appropriate.

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: 'Создаёт новую позицию номенклатуры (товар/услуга)', and 'новую' implicitly sets it apart from the update_nomenclature sibling. It never names an alternative tool explicitly, so sibling differentiation is left to inference rather than stated.

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 a concrete procedure: a dry-run by default, show the user the payload, then repeat with confirm=true after consent. That is clear operational context, but there is no guidance on when to choose a different tool, such as create_folder for grouping or update_nomenclature for existing items.

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