Skip to main content
Glama
Yandex Direct MCP

Yandex Direct MCP

Сводка по клиентам

clients_overview
Read-onlyIdempotent

Get a one-call overview of managed Yandex Direct client accounts: balances, campaign counts by state and moderation, and optional impressions, clicks, and spend by period.

Instructions

Сводка по всем клиентам агентства и кабинетам в управлении за один вызов — для вопросов вроде «что у меня по аккаунтам в управлении»: по каждому клиенту баланс общего счёта и число кампаний по состояниям (on — идут или могут идти, suspended — остановлены пользователем, off — не идут по другой причине, ended) и статусам модерации (moderation, rejected, draft). Архивные кампании не считаются. Клиенты — из list_clients, либо явный список logins. Ошибка по одному клиенту (нет доступа, нет общего счёта) не прерывает остальных и попадает в его строку. С параметром stats добавляет показы, клики и расход (с НДС, в валюте клиента) за период — по одному отчёту Reports на клиента, строго по очереди: Яндекс пускает примерно один отчёт в 10 секунд, так что 30 клиентов — около 5 минут; клиенты без неархивных кампаний не запрашиваются, а кто не уложился в 5 минут, помечается statsSkipped. Без stats ответ приходит за секунды — запрашивать расход, только когда вопрос про деньги или трафик. Не вызывать list_campaigns по каждому клиенту в цикле — эта сводка дешевле. Тратит баллы API каждого клиента: один запрос кампаний на клиента и один запрос баланса на 50 клиентов у агентства (у обычного аккаунта — на каждого). Кампании клиентов читаются через API v501, в песочнице — через v5.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "clients_overview"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoСколько клиентов обойти, 1–200. По умолчанию 50.
statsNoДобавить показы, клики и расход за этот период. Медленно: около 10 с на клиента.
loginsNoТолько эти логины клиентов. По умолчанию — все из list_clients.
searchNoТолько клиенты, у которых логин или название содержит эту подстроку.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.6.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile, but the description adds substantial behavior: archived campaigns are excluded from counts, a per-client failure (no access, no shared account) does not abort the run and is surfaced in that row, stats is strictly sequential at roughly one report per 10 seconds (~5 min for 30 clients), clients with no non-archived campaigns are skipped, and stragglers past 5 minutes are flagged statsSkipped. It also discloses API point consumption per client and the v501/v5 sandbox difference.

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?

Purpose and the stats cost warning are front-loaded, and nearly every clause carries operational information. The single dense paragraph is long and would read better broken into purpose / when-to-use / cost sections, but there is little filler.

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

Completeness5/5

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

With no output schema, the description carries the return-value burden and does: balance per client, campaign counts by state and moderation status, and the added showings/clicks/spend figures with VAT in the client currency. Combined with the failure and timeout semantics, an agent knows what it will get and how long it will take.

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, but the description adds meaning beyond it: stats pulls one Reports request per client, costs about 10 seconds each, and can yield statsSkipped instead of numbers, which changes how an agent should interpret the response. It also clarifies that logins is an alternative to the default list_clients source and that limit governs how many clients are traversed.

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?

States a specific deliverable: a one-call summary of all agency clients and managed accounts, with exactly what each row contains (shared-account balance, campaign counts by state and moderation status). It explicitly distinguishes itself from list_clients (source of the client list) and from looping list_campaigns, so an agent can place it among siblings without opening schemas.

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

Usage Guidelines5/5

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

Gives a concrete triggering question ("что у меня по аккаунтам в управлении"), an explicit rule for when to add stats (only when the question is about money or traffic), an explicit anti-pattern (don't call list_campaigns per client in a loop — this is cheaper), and names the refused alternative. Nothing is left to inference.

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