Запрещённые площадки кампании

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

Annotations already declare destructiveHint=true, so the description's job is to say what gets destroyed and under which mode — which it does ('прежние площадки теряются, пустой массив очищает'). It also discloses a hidden cost that annotations cannot convey: add and remove perform an extra API read of the current list. It stops short of failure modes (what happens past 1000 sites, partial failures), so not a full 5.

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?

Three front-loaded sentences with no filler: what the tool manages, how modes behave, and where to read the current state. The one-sentence anti-pattern warning is placed where it lands hardest.

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 3-parameter destructive mutation with no output schema, the description covers scope, mode semantics, read-alternative, and the destructive consequence — everything needed to call it safely. Minor gap: behavior at the 1000-site boundary and error/pagination feedback are unaddressed.

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% and the schema already spells out each mode value, the sites format, and that add/remove read the current list first. The description largely restates the same mode semantics rather than adding new meaning, so 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 pair (set the excluded sites for a campaign), the object type (RSYA sites and apps), and a hard cap (up to 1000). An agent can distinguish it immediately from get_campaign (read) and from set_campaign_blocked_ips (a different exclusion type).

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?

Explicitly names the required mode and what each value does, points to get_campaign as the read path, and gives a concrete warning about the most likely mistake (using replace with a single site erases the rest — use add instead). Both when-to-use and when-not-to are covered.

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