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

Annotations only declare readOnlyHint=false and openWorldHint=false; the description adds the substantive behavior an agent cannot infer: a preflight count runs first and nothing is sent yet, duplicates already present in the target are skipped, route delay and publication windows do not apply, ordering is oldest→newest one at a time, and the operation can be paused or cancelled. It also discloses the paid-plan gate and the one-import-per-route lock.

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?

Front-loaded with the verb and scope, and nearly every sentence carries a distinct constraint or behavior. It is a single dense paragraph of run-on clauses, so scanning for a specific rule (limit caps, lastPostId, paid plans) is harder than it needs to be.

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 usefully explains that the call first returns a count of matching posts before anything is sent. It covers sources, caps, prerequisites, and failure recovery, but never points to import_show for checking progress, which an agent would need after starting a long migration.

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, but the description earns extra credit: it explains why limit takes typical values of 10/50/100/500 and cannot exceed 500, and it supplies the operational meaning of lastPostId (only needed when the prior import failed because the service had seen no posts; not needed for MAX). The handling of selected is slightly at odds with the parameter existing, though the schema clarifies.

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 precise verb and resource — 'Начинает перенос истории по маршруту' — and immediately scopes it (последние посты источника 10/50/100/500, источник → приёмник). An agent can tell this apart from import_pause/import_cancel/import_show because the description says the migration can be paused or cancelled, implying those siblings handle it.

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 states the situation for use (заполнить новый канал), the hard constraints (не больше 500; один перенос за раз на маршрут; только платные тарифы; только источники Telegram и MAX), and even the recovery path: re-run with lastPostId if the previous Telegram import didn't start. It also explains that selected transfers are done in the cabinet or bot, which routes the agent away from trying that via API.

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