Вход в Яндекс.Директ: код

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

With only readOnlyHint=false and openWorldHint=true supplied, the description carries real weight and delivers: it discloses a persistent local side effect (the token is saved on this computer) and an easily-misread response property (the token is not returned). What it omits is failure behavior — e.g. what happens with an expired or reused code — which the schema partly covers.

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 compact sentences that lead with the step position and the core action, then immediately clarify the most likely misconception (the token is not in the response). No filler.

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 single-parameter login-completion tool with no output schema, the key missing context would be whether a token is returned and where it goes — both are addressed explicitly. Combined with the fully documented parameter, an agent has everything needed to call it correctly.

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?

Schema description coverage is 100% and the 'code' property already documents its one-time, ~10-minute nature and its origin in start_login. The description only restates that the code comes from the user, adding no new semantics beyond the schema, so the baseline of 3 applies.

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 names a specific verb and transformation — exchanging the user's confirmation code for a token and persisting it locally — plus it positions itself as 'the second step of login'. That implicitly separates it from start_login/auth_status/logout, but the sibling is never named, so an agent must infer the ordering rather than read it explicitly.

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?

Positioning it as 'the second step of login' implies it should only be called after the user has obtained a code, and the schema notes the code comes from start_login. However, there is no explicit when-not guidance (e.g. what to do if the code has expired or if already authenticated via auth_status), so usage is only implied.

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