Отключить Метрику

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

The annotations already indicate destructiveHint=true, but the description adds important context: what exactly is deleted, what remains (env token), and that the app's access stays active on Yandex's side. This exceeds what annotations provide alone.

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 sentences, each providing distinct value: the primary action, the exception, and the side effect. No fluff or redundancy.

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 destructive action with robust annotations and no output schema, the description fully covers what an agent needs to know: what is affected, what isn't, and the external implication.

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?

There are zero parameters, so the description doesn't need to explain any. It correctly focuses on the effect of the operation itself.

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 clearly states that the tool removes the saved Metrika token from disk, and distinguishes it from the environment variable token. It uses precise language and is not a tautology.

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 explains what the tool does and explicitly mentions what it does NOT do (env var token). It doesn't explicitly compare to siblings like start_login or finish_login, but the context makes it clear this is a logout operation.

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