Удалить подключение к ИИ

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

Beyond the annotations, the description reveals important behavior: deletion destroys saved keys, deletion is blocked while the connection is still referenced, and the agent must first detach it from bots, knowledge bases, and AI Reply nodes. This is rich, non-obvious context that annotations alone do not provide.

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?

The description is only two sentences: the first front-loads the core destructive action, and the second compactly lists the necessary dependency-clearing steps. Every sentence earns its place, and there is no filler.

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 destructive delete tool with no output schema, the description covers the effect, the sensitive-data consequence, the blocking condition, and the exact steps to unblock it. This is sufficient for an agent to invoke the tool correctly and avoid failed calls.

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 documents both parameters. The description does not add significant new direct meaning for the provider or case parameters, though it does mention provider_id in flows_save as part of the unblocking workflow. Baseline 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 starts with a specific verb and resource: 'Удаляет подключение вместе с сохранёнными ключами' — it clearly states what is deleted and that saved keys are also removed. This distinguishes it from sibling AI tools like ai_save, ai_list, and ai_test.

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?

The description explicitly explains when deletion is blocked ('Пока сервис используют боты, панель удалить его не даст') and provides precise removal steps using sibling tools with parameter values: bots_save ai_provider=null, knowledge_save provider=null, and flows_save. This gives the agent clear conditions and alternatives.

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