tool_hint

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

There are no annotations, so the description carries the burden. It discloses that the tool 'Отвечает каким тулом и почему'—it responds with a tool recommendation and explanation—and does not claim to execute the selected tool. However, it does not explain how routing decisions are made, whether there are limitations, or any side effects beyond returning a recommendation.

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 short and front-loaded: the first sentence identifies it as a router, the second documents the parameter, and the third gives optional motivation. The third sentence is somewhat promotional ('−260% selection quality') and not operationally necessary, but the overall structure remains compact.

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 one-parameter, low-complexity tool with an output schema present, the description covers the core invocation needs: what the tool is for, what input to provide, and what kind of answer to expect. Missing only minor details like explicit wording guidelines for the 'what' value, but nothing critical for correct use.

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 input schema has 0% description coverage, but the tool description fully documents the only parameter: 'what — действие/вопрос', with concrete examples. This is sufficient for an agent to know exactly what to pass into this single optional string parameter.

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 is a router which answers which tool to use for a given action/question and why, e.g., 'анализ страницы', 'мониторинг', 'статьи'. This is a specific, recognizable purpose, but it does not explicitly differentiate itself from the sibling router-like tool 'service_route'.

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 tells the agent to use this tool instead of blindly trying all 57 tools—'вместо перебора 57 тулов вслепую'—and that the input should be an action or question. It conveys when to use it, though it does not name a specific alternative tool or state when not to use it.

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