Skip to main content
Glama
askads

VK Ads MCP

Создать кампанию (ad_plan)

create_ad_plan

Create a VK Ads campaign by setting name, budget, dates, objective, and auction strategy. Pass advanced fields via extra parameters to tailor the API request to your needs.

Instructions

Создаёт кампанию (ad_plan). Денежные поля — в валюте аккаунта. Сложные и редкие поля передаются через extra (подмешиваются в тело запроса как есть).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesНазвание кампании.
extraNoДополнительные поля кампании, подмешиваемые в тело запроса (например, priced_goal, pricelist_id).
dateEndNoДата окончания, YYYY-MM-DD.
maxPriceNoПредельная ставка в валюте аккаунта.
dateStartNoДата начала, YYYY-MM-DD.
objectiveNoЦель кампании, например site_conversions, leadads, traffic.
budgetLimitNoОбщий бюджет в валюте аккаунта.
budgetLimitDayNoДневной бюджет в валюте аккаунта.
autobiddingModeNoСтратегия аукциона, например max_goals, fixed, second_price_mean.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv1.5.0
    • changedInput schema / properties / autobiddingMode / description
      Previous value: -"Auction strategy, e.g. max_goals, fixed, second_price_mean."New value: +"Стратегия аукциона, например max_goals, fixed, second_price_mean."
    • changedInput schema / properties / budgetLimit / description
      Previous value: -"Total budget in account currency."New value: +"Общий бюджет в валюте аккаунта."
    • changedInput schema / properties / budgetLimitDay / description
      Previous value: -"Daily budget in account currency."New value: +"Дневной бюджет в валюте аккаунта."
    • changedInput schema / properties / dateEnd / description
      Previous value: -"End date YYYY-MM-DD."New value: +"Дата окончания, YYYY-MM-DD."
    • changedInput schema / properties / dateStart / description
      Previous value: -"Start date YYYY-MM-DD."New value: +"Дата начала, YYYY-MM-DD."
    • changedInput schema / properties / extra / description
      Previous value: -"Extra ad plan fields merged into the body (e.g. priced_goal, pricelist_id)."New value: +"Дополнительные поля кампании, подмешиваемые в тело запроса (например, priced_goal, pricelist_id)."
    • changedInput schema / properties / maxPrice / description
      Previous value: -"Bid cap in account currency."New value: +"Предельная ставка в валюте аккаунта."
    • changedInput schema / properties / name / description
      Previous value: -"Ad plan name."New value: +"Название кампании."
    • changedInput schema / properties / objective / description
      Previous value: -"Campaign objective, e.g. site_conversions, leadads, traffic."New value: +"Цель кампании, например site_conversions, leadads, traffic."
  2. Changed3 schema fields changedv1.1.4
    • removedInput schema / properties / dateEnd / $ref
      Removed value: -"#/properties/dateStart"
    • addedInput schema / properties / dateEnd / pattern
      Added value: +"^\\d{4}-\\d{2}-\\d{2}$"
    • addedInput schema / properties / dateEnd / type
      Added value: +"string"
  3. First observedv1.1.3

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already indicate this is a non-read-only, non-idempotent operation. The description adds useful behavioral context beyond the schema: money fields use account currency, and `extra` is injected into the request body verbatim. It does not contradict any annotation.

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

Conciseness5/5

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

The description is three short sentences with no redundancy. The core purpose comes first, followed by two high-value usage notes. Every sentence earns its place.

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

Completeness4/5

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

Given the rich input schema, annotations, and the extra-field mechanism, the description is largely complete for correct invocation. It could additionally mention what the tool returns or that existing campaigns should be modified via update_ad_plan, but these are minor gaps given the strength of the structured context.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds a cross-cutting semantic rule: all monetary parameters are in account currency, and complex/rare fields should be routed through `extra`. This helps the agent choose the right place for uncommon parameters even when they are not explicitly listed in the schema.

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

Purpose5/5

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

The description states a specific action and resource: 'Создаёт кампанию (ad_plan)' — creates a campaign/ad_plan. This clearly differentiates the tool from sibling tools like update_ad_plan or list_ad_plans.

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

Usage Guidelines4/5

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

The description provides clear practical context: money fields are in account currency, and complex/rare fields should be passed via `extra`, which is mixed into the request body as-is. It does not explicitly name alternatives like update_ad_plan, but the creation intent is unambiguous and the guidance is directly actionable.

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