Ответить собеседнику

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

Beyond the annotations, the description discloses important side effects: by default the dialog switches to manual mode and is assigned to the user, the scenario stops until explicitly returned, and messages are saved even if Telegram rejects them. It also preconditions that the bot must be running and directs attention to the 'ошибка доставки' field. This is substantial behavioral detail with no contradiction to 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?

The description is three dense sentences with no filler. The purpose is front-loaded, followed by the most impactful behavioral caveat (manual mode takeover), and then the operational requirement and response field. Every sentence earns its place.

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 mutation tool with 5 parameters, the description covers the main behavior, the mode switch side effect, how to revert it, a runtime prerequisite, and an important response nuance. Although there is no output schema, the description names the critical response field to check. Nothing essential appears missing for correct invocation.

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 coverage is 100%, so the baseline is 3. The description adds meaningful extra semantics: reply is an alternative to text, not combined with it ('Вместо text, а не вместе с ним'), take_over defaults to true, and case has a fallback resolution order. This elevates the parameter guidance beyond the schema.

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 a specific verb and resource: 'Отправляет сообщение человеку от имени бота' — sending a message on behalf of the bot. It clearly distinguishes the two input modes (own text vs. prepared reply from replies_list), separating it from related dialog tools like dialogs_update and dialogs_delete.

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 gives clear context: the bot must be running, and the tool can send either free text or a prepared reply. It also references dialogs_update mode=bot as the way to return the dialog to the scenario, and mentions the delivery-error field. It does not explicitly state when not to use this tool, but the context is strong enough for an agent to select it appropriately.

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