Выход из Директа

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

Annotations already declare destructive=true and readOnly=false. The description goes beyond them by naming exactly what is removed (the saved login on this machine), what survives it (the YANDEX_DIRECT_TOKEN environment variable), and where the side effect of revoking app access actually happens (Yandex ID). The only gap is that it does not state whether a re-login is required afterward.

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?

Two short sentences; the first gives the core action, the second gives the important boundaries of that action. Nothing is repeated and nothing is wasted.

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 the tool takes no parameters and has no output schema, and because the annotations state the full safety profile, this is nearly complete. The only small omission is the post-logout state: whether the session ends, or whether the agent must call start_login again.

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 takes zero parameters, so the schema sets the baseline at 4. There is nothing the description could add about parameters, and none is needed.

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 states a specific verb and a specific resource: it deletes the saved login from the dialog on this computer. It also distinguishes this tool from nearby siblings such as start_login, finish_login, and auth_status by making clear that the target is local saved credentials, not the token or the app authorization.

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 implicitly tells the agent when not to use this tool: it notes that YANDEX_DIRECT_TOKEN is left untouched and that app access is revoked in Yandex ID, which signals that this is not the tool for revoking app authorization. It does not explicitly name an alternative tool, but the exclusions from scope are clear.

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