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

yandex-direct-mcp-plus

by Pavelsiba

Список ключевых слов

list_keywords
Read-only

Retrieve keywords in specified Yandex.Direct ad groups, including bids, statuses, and optional statistics or autotargeting settings by specifying fields.

Instructions

Ключевые фразы в группах объявлений: фразы, ставки (руб), статусы. По умолчанию возвращается узкий набор полей; нужны другие (StatisticsSearch, StatisticsNetwork, Productivity, ServingStatus и прочие из KeywordFieldEnum) — перечислите их в fields. Автотаргетинг — спецфраза ---autotargeting в той же группе; его категории запросов — с autotargeting: true.

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": {
      "ad_group_ids": "<ad_group_ids>"
    },
    "name": "list_keywords"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoСколько объектов вернуть (максимум 10000)
fieldsNoКакие поля вернуть; по умолчанию Id, Keyword, CampaignId, AdGroupId, Status, State, Bid, ContextBid
offsetNoСмещение выборки: сюда передаётся LimitedBy предыдущей страницы
ad_group_idsYesГруппы, ключевые фразы которых нужно выбрать
autotargetingNotrue — добавить к ответу AutotargetingSettings: категории запросов и брендов у фразы ---autotargeting (YES/NO). У обычных фраз поле пустое

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 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
    • addedInput schema / properties / autotargeting
      Added value: +{
      +  "description": "true — добавить к ответу AutotargetingSettings: категории запросов и брендов у фразы ---autotargeting (YES/NO). У обычных фраз поле пустое",
      +  "type": "boolean"
      +}
  2. First observedv1.6.1

TDQS

A3.7/5.0
Behavior4/5

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

The annotations already carry the safety profile (readOnlyHint, openWorldHint), yet the description still adds useful behavior: the default is a narrow field set, bids are in rubles, and the pseudo-phrase ---autotargeting appears in the same ad group with its own request categories. It does not mention pagination, but the schema covers offset and limit.

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?

Three dense sentences lead with what is returned, then cover the fields option, then the autotargeting special case. Nothing is obviously redundant, though the notation is compact enough to need care when reading.

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?

For a five-parameter list tool with no output schema, this description covers what the objects are, the default fields, and the autotargeting edge case. Paging behavior is left to the schema's offset description, which is acceptable.

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%, so the baseline is 3. The description does add meaning: it lists optional fields from KeywordFieldEnum and explains that autotargeting:true attaches AutotargetingSettings for ---autotargeting. That is real value beyond the schema, but the description does not go deeper into limit or offset.

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 concrete verb and resource: it returns keyword phrases for ad groups, with bids and statuses. This is enough to tell it apart from list_ad_groups and list_ads, but the description never names a sibling tool explicitly.

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 description is clearly about reading keywords, and it explains when to populate fields: the default returns a narrow set, so ask for more if you need them. It does not give explicit routing guidance, such as using add_keywords, update_keywords, or get_statistics instead for other tasks.

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