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

The description discloses key behavioral traits: it charges from the agent balance, can return a payment_required error, and is idempotent per agent. Since no annotations are provided, this description carries the full burden and covers the essential side effects.

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?

The description is exceptionally concise, using three sentences to convey purpose, pricing, error handling, and idempotency. It contains no redundant words or unnecessary details.

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?

The description covers the tool's purpose and error handling, but omits what the actual return value looks like (e.g., proxy address, credentials) and the meaning of `count` and `period_days`. Given there is no output schema, these gaps are noticeable and could hinder correct usage.

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 parameters `count` and `period_days` have defaults but their meaning is entirely absent. The description does not explain what these parameters do, leaving the agent to guess (e.g., number of proxies, lease duration). Only `agent_id` is inferable from the description text.

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 the tool obtains a Russian IP proxy to access RU-only sites, listing concrete examples (Wildberries, Ozon, Yandex, hh.ru, Avito). It distinguishes itself from sibling tools like fetch_ru or fetch_web by focusing on the proxy acquisition rather than direct fetching.

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?

It specifies the use case (accessing RU-only sites) and provides a conditional instruction: if payment_required is returned, call topup_balance and retry. It does not explicitly mention when not to use it, but the context is clear enough.

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