Skip to main content
Glama
Yandex Direct MCP

Yandex Direct MCP

Действие с кампаниями

campaign_action
Destructive

Apply suspend, resume, archive, unarchive, or delete actions to Yandex Direct campaigns by ID through API v501, using v5 in the sandbox.

Instructions

Выполняет действие над кампаниями по id: suspend, resume, archive, unarchive или delete. Запрос идёт в API v501, в песочнице — в v5.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>",
      "ids": "<ids>"
    },
    "name": "campaign_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYesId кампаний, к которым применить действие.
actionYes
client_loginNoЛогин клиента агентства или кабинета в управлении (из list_clients). Если не указан — YANDEX_DIRECT_LOGIN из конфигурации, а без него собственный аккаунт токена.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.6.0
    • addedInput schema / properties / client_login
      Added value: +{
      +  "description": "Логин клиента агентства или кабинета в управлении (из list_clients). Если не указан — YANDEX_DIRECT_LOGIN из конфигурации, а без него собственный аккаунт токена.",
      +  "pattern": "^[A-Za-z0-9][A-Za-z0-9._@-]{0,99}$",
      +  "type": "string"
      +}
  2. Changed1 schema field changedv1.5.1
    • changedInput schema / properties / ids / description
      Previous value: -"Campaign ids to act on."New value: +"Id кампаний, к которым применить действие."
  3. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the risk profile is covered. The description adds a genuinely useful detail not in annotations — request routing to API v501, and v5 in the sandbox — but says nothing about batch semantics (partial failure, per-id results) or whether delete is irreversible, which matters for a destructive multi-id call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the verb and action list, with no filler. The sandbox/API-version sentence is somewhat incidental but is factually relevant to execution, so it earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, non-idempotent, multi-id mutation with no output schema, the definition leaves key blanks: whether the operation is atomic, what happens on invalid or already-archived ids, and what the response contains. Annotations cover the safety profile, so the remaining gap is real but not severe.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% and the schema already documents ids, the action enum's allowed values, and the client_login fallback chain in detail. The description merely restates the action names and 'by id', adding no syntax, format, or constraint meaning beyond the input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb (performs an action) plus the resource (campaigns by id) and enumerates the five supported actions, so an agent knows exactly what the tool does. It does not explicitly contrast itself with siblings like update_campaign, but the id-list action model is distinct enough to be recognizable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: listing suspend/resume/archive/unarchive/delete suggests this is the tool for those state changes, and the id-based signature implies bulk operation. There is no explicit when-to-use vs. when-not guidance and no mention of alternatives such as update_campaign for field edits.

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