Запустить рассылку

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

Beyond the annotations (destructiveHint=true, openWorldHint=true), the description explains the irreversible consequence: 'Отправленное не отзывается ни у одного получателя' (sent cannot be recalled), and reveals queueing, scheduling via run_at, and the all-recipients risk. This significantly exceeds the 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?

Four short sentences, each with a distinct purpose: queueing, irreversibility warning and preview, scheduling, and cancellation. The action is front-loaded and there is no filler.

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 three-parameter tool with no output schema, this description is unusually complete: it covers the core action, the main risk and mitigation, scheduling semantics, and the follow-up cancel action. Nothing essential for a correct invocation is missing.

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 already documents every parameter (100% coverage), so the baseline is 3. The description adds rationale for confirm_title as an exact-title confirmation and clarifies scheduling behavior with run_at, adding semantic value 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 immediately states a specific action and scope: 'Ставит черновик в очередь' (puts a draft into the send queue), which clearly means starting a broadcast. It also distinguishes itself from adjacent siblings by referencing broadcasts_preview and broadcasts_cancel, and from broadcasts_save by emphasizing the draft is already prepared.

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 gives explicit workflow guidance: first use broadcasts_preview to check recipients, and use broadcasts_cancel for anything not yet sent. The warning that an empty selection means all bot interlocutors tells the agent when to be cautious and what to check beforehand.

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