Skip to main content
Glama
yandex-direct-mcp-plus

yandex-direct-mcp-plus

by Pavelsiba

Стратегия кампании

get_strategy
Read-only

Retrieves a text-graphic campaign's current ad delivery strategy, priority goals and values, Metrica counters, and attribution model so you can inspect bidding and goal setup.

Instructions

Получить текущую стратегию показов текстово-графической кампании вместе с целями (PriorityGoals), счётчиками и моделью атрибуции. Реальные ID целей Метрики, по которым работает кампания, — TextCampaign.PriorityGoals.Items[].GoalId (рядом их ценность Value в рублях), счётчики — CounterIds. GoalId внутри BiddingStrategy бывает служебным: 13 — «оптимизировать по ключевым целям», то есть по тем же PriorityGoals; 12 — «Вовлечённые сессии». Названий целей API Директа не отдаёт — они есть только в Метрике.

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": {
      "campaign_id": "<campaign_id>"
    },
    "name": "get_strategy"
  }
}

Input Schema

NameRequiredDescriptionDefault
campaign_idYesID текстово-графической кампании

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.1.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
  2. First observedv1.6.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already mark this as a safe read, yet the description adds real behavioral context beyond them: the service GoalId values 13 and 12 must be resolved through PriorityGoals, and Direct API never returns goal names. This is the kind of interpretation hint an agent cannot get from the structured fields. It stops short of covering failure modes, e.g. behaviour for a non-text campaign or one with no strategy.

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?

It is dense and front-loaded, leading with the purpose and then the field paths an agent will actually encounter. Every sentence carries information, though the transition from return fields into the GoalId caveats is abrupt enough that a short connector or bullet list would aid scanning.

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?

There is no output schema, so the description must carry the return shape itself, and it does: PriorityGoals.Items[].GoalId with ruble Values, CounterIds, attribution model, plus the caveat that goal names live only in Metrica. Only error/edge-case behaviour for campaigns lacking a strategy is left uncovered.

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 100% and the single campaign_id description in the schema is effectively identical to the wording in the tool description, so no additional meaning is layered on top. Baseline 3 applies; the rest of the description is spent on return-value shape, which is legitimate but belongs to other dimensions.

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 opens with a specific verb and resource ("Получить текущую стратегию показов текстово-графической кампании") and enumerates what is returned alongside it: PriorityGoals, counters, attribution model. This clearly separates it from the mutation sibling set_strategy and from the generic get_campaign without opening either schema.

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?

The read intent is implied and complements set_strategy, but the description never states when to call it versus alternatives (e.g. get_campaign, which may also carry strategy data) or any prerequisite such as needing a text-campaign ID. Usage is inferable from the wording rather than spelled out.

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