Вход в Яндекс.Директ: ссылка

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

The description adds genuinely useful behavior the annotations omit: no manual token needed, the tool returns a URL rather than performing auth, and a repeated call invalidates the prior link. However, that invalidation side effect is in tension with the declared idempotentHint=true, since calling twice produces an observably different state than calling once. The description is the more accurate party here, but it still leaves link lifetime/expiry and any modal or scope selection undisclosed.

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, front-loaded with what the tool returns, then how to use the result, then the caveat. Every clause carries information an agent needs; nothing is repeated from the schema or title.

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, no-output-schema auth entry point, the description covers the return value (a link), the handoff to finish_login, and the repeat-call caveat. Missing only ancillary facts such as link expiration time and whether the call fails if a session already exists.

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 there is nothing for the description to disambiguate; the baseline applies. It does usefully clarify that identity is not supplied as an argument but obtained out-of-band via a Yandex page.

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?

"Первый шаг входа из диалога... возвращает ссылку на вход в Яндекс" states a specific action (returns a Yandex login URL) and its place in the auth flow. It separates itself cleanly from the siblings finish_login and auth_status, which an agent reading only names could easily confuse.

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?

Explicit sequencing: show the returned link to the user, then pass the code from the Yandex page to finish_login. It also warns that a repeat call invalidates the previous link, which is a real usage constraint. It stops short of saying when NOT to call it (e.g., already authenticated — call auth_status instead), so it is not a full 5.

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