Ответить собеседнику

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

The annotations only provide basic flags (readOnly=false, openWorld=true, etc.), but the description discloses critical behavioral traits not covered by annotations: the dialog is moved to manual mode and assigned to the user by default, the scenario pauses until restored via dialogs_update, and the 'ошибка доставки' field indicates that the message may be persisted even if Telegram delivery failed. This goes well beyond structured 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 sentences, tightly written, with the primary purpose stated first, followed by essential side effects and a practical warning. Every sentence adds value with no filler or redundancy.

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?

Even though there is no output schema, the description covers the key operational aspects: prerequisites (bot must be running), side effects (manual mode transition), remediation (dialogs_update mode=bot), and error handling (delivery error field). This is sufficient context for an agent to anticipate consequences and monitor success, especially for a message-send operation.

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 schema description coverage is 100% for all four parameters, so the baseline is 3. The description does not add significant parameter-specific semantics beyond the schema; it reinforces the take_over behavior already described in the schema and mentions the delivery-error response field, but does not introduce new meanings for 'dialog' or 'text' parameters.

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 'Отправляет сообщение человеку от имени бота' (sends a message to a person on behalf of the bot), clearly specifying the verb and resource. It distinguishes from siblings like dialogs_list, dialogs_get, dialogs_history, dialogs_update, and dialogs_delete, which handle reading or updating dialog metadata rather than sending messages.

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 provides context on when to use the tool by explaining the default behavior (dialog switches to manual mode) and explicitly references dialogs_update mode=bot as a way to restore bot control, giving a relevant alternative/consequence. It also states the prerequisite that the bot must be running. However, it does not explicitly enumerate when NOT to use this tool versus other dialog tools, so it lacks a direct exclusion.

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