Statsnet

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

No annotations are provided, so the description must carry the behavioral load. It does disclose the return format (Markdown) and the content of the card, which is genuinely useful, but says nothing about auth requirements, rate limits, or behavior when the company/identifier is not found.

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?

A single compact sentence that front-loads the resource and lists the payload contents without filler. Efficient, though it is thin enough that a bit more routing detail would have been worth the bytes.

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 no output schema, the description does the necessary work of telling the agent what the return contains and in what format. The main gap is the absence of the two-parameter contract explanation (jurisdiction/identifier pairing) and error behavior.

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 only 50%: identifier is documented (БИН/ИИН) but jurisdiction's enum values carry no description. The description adds no parameter meaning at all — no explanation of the jurisdiction codes or of which identifier formats are accepted per jurisdiction.

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 resource — a public company card — and enumerates its sections (status, registration, management, indicators, finances), which is far more than a restatement of the name. It implicitly contrasts with the sibling search_companies by describing a single-company profile, though it never names that alternative.

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?

There is no when-to-use guidance and no mention of the sibling search_companies, which is the obvious alternative for finding companies. An agent must infer that this tool is for fetching full detail on an already-known company.

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

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

Аннотации отсутствуют, поэтому вся поведенческая нагрузка ложится на описание. Оно сообщает только, что возвращается список совпадений; не раскрыты пагинация, влияние limit, ограничения jurisdiction, права доступа или поведение при отсутствии совпадений.

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?

Два коротких предложения без воды: сначала назначение и критерии поиска, затем формат возврата и связь с get_company. Информация подана с самого начала.

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?

Для поискового инструмента с 3 параметрами, без выходной схемы и аннотаций описание покрывает назначение и тип результата, но не объясняет limit, jurisdiction и поведение при множественных совпадениях. Этого достаточно для базового вызова, но не полностью.

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?

Покрытие описаниями в схеме 67%: query и jurisdiction документированы, limit — нет. Описание добавляет смысл query (название/БИН-ИИН/ФИО), но ничего не говорит о limit и jurisdiction сверх того, что уже есть в схеме. Базовый уровень 3 уместен.

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?

Указан конкретный глагол и ресурс (поиск компаний и ИП), перечислены ключевые поля поиска (название, БИН/ИИН, руководитель) и формат результата. Фраза 'для get_company' явно отличает инструмент от соседнего get_company.

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?

Из формулировки ясно подразумевается сценарий: сначала поиск через search_companies, затем получение деталей через get_company. Однако нет явных указаний, когда этот инструмент не подходит или какие есть альтернативы, кроме одного упомянутого соседа.

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