Отключить Вебмастер

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

The description adds meaningful behavioral detail beyond the destructiveHint=true annotation: it specifies the disk token deletion, explicitly says the env token is preserved, and notes that Yandex-side access remains active until revoked. No contradiction with annotations.

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?

Three short sentences deliver complete information without redundancy: what is deleted, what is not deleted, and the external side effect. The most important action is front-loaded.

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 no-parameter logout tool with destructive annotations, the description fully covers the action, boundary conditions, and external persistence. No output schema is needed for this operation.

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?

The tool has zero parameters and schema coverage is 100%, so the description is not required to explain parameter meaning. It correctly focuses on behavior rather than inputs.

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: 'Удаляет сохранённый токен Вебмастера с диска' (deletes the saved Webmaster token from disk). This clearly distinguishes logout from sibling auth tools like auth_status, start_login, and finish_login.

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 explicit when-not guidance: the YANDEX_OAUTH_TOKEN environment variable is not touched and requires manual removal. It also directs users to Yandex ID to revoke the still-active access, providing an alternative for full logout.

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