Начать подключение Метрики

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

The annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds meaningful behavioral context beyond those hints: no config editing or client restart is required, the code expires in 10 minutes, and the code can only be exchanged by this server. It does not discuss exact return URL format or error conditions, but the safety profile is already covered by 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?

Every sentence adds a distinct piece of information: the step's role, the no-config/no-restart property, the returned link, the exact user actions, the handoff to finish_login, the 10-minute validity, and the security property. There is no filler or repetition.

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 zero-parameter first step of a two-step flow, the description is nearly complete: it explains what is returned, what the user must do, where the code goes next, and the code lifetime. It does not mention what to do if the user is already authenticated, but that is a minor gap given the sibling auth_status tool and the focused scope.

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, so the schema carries no burden; the baseline is 4. The description clarifies that no configuration changes are needed and focuses on the returned OAuth link rather than any inputs, which is sufficient for a parameterless tool.

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 'Первый шаг подключения Яндекс Метрики', naming a specific action (starting Yandex Metrika OAuth connection) and its resource. It also differentiates itself from the sibling finish_login by explicitly stating that the received code must be passed to finish_login, so an agent can distinguish the two halves of the flow.

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 provides explicit user-facing instructions: show the full link, ask the user to open it in a browser under an account with access to the needed counters, confirm access, and send back the confirmation code. It also names the follow-up tool finish_login, making the intended sequence unambiguous.

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