Кому уйдёт рассылка

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses meaningful behavior: it saves nothing, limits the recipient list to the first 50 by freshness, reports how many recipients muted the bot, and flags risky message conditions such as empty selection, overly broad selection, and unknown substitutions. This is substantial context that is not visible from annotations alone.

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: first it states the purpose and outputs, then the urgency rationale, then side effects and filter semantics. The most important operational fact is front-loaded.

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 no output schema, the description needs to convey what the tool returns, and it does: counts, the first 50 recipients, muted-recipient counts, and message-level warnings. It also covers side effects (none), the alternative for drafts, and default filter behavior, making it complete enough for an agent to invoke the tool correctly.

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 description coverage is 100%, so the parameters are already documented individually. The description adds valuable collective semantics by stating that the conditions are the same as those in the conversation list and that omitting all conditions means all bot interlocutors, which helps an agent reason about how the filter parameters combine.

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 begins with 'Прикидка до отправки' ('estimate before sending'), naming a specific action and resource, then lists concrete outputs: matching conversation count, who qualifies (first 50 by freshness), how many muted the bot, and warning conditions. It also explicitly distinguishes itself from broadcasts_save ('черновик заводит broadcasts_save'), so an agent can separate it from sibling tools.

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 a clear when-to-use instruction: 'Разосланное не отзывают, поэтому смотреть надо здесь' — check here before sending because sent broadcasts cannot be recalled. It also names the alternative for saving a draft ('Ничего не сохраняет: черновик заводит broadcasts_save') and explains filter defaults ('ни одного условия означает всех собеседников бота').

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