Отправить пробу рассылки

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

Annotations already declare destructive=true, non-idempotent and open-world. The description adds real behavioral value beyond them: that a message is genuinely delivered to a live dialog on behalf of the broadcast bot (not simulated), which is the key fact an agent needs before triggering it. It still omits rate limits or side effects of the send.

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?

A single front-loaded sentence that leads with the most consequential fact ('Реально отправляет') and wastes no words.

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?

With 100% schema coverage, full annotations and no output schema, the description only needs to add behavioral framing, which it does. It could note that confirm_name is a safety gate, but for a destructive send the essential fact is present, so it is nearly complete.

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 each parameter (case, dialog, broadcast, confirm_name) is already documented in the schema. The description only refers to 'the selected dialog', adding no syntax or selection detail beyond the schema, so the baseline 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?

States a specific verb and resource: it sends one real message to the selected dialog as the broadcast bot. The word 'проба' (trial) and 'одно сообщение' (one message) differentiate it from a full launch, though no sibling is named 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?

'Реально отправляет' (actually sends) implicitly contrasts with a preview/dry-run, so the intended use — a trial send before launching — is inferable. However, no alternative sibling (broadcasts_preview, broadcasts_start) is named and no prerequisites or when-not-to-use are given.

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