Skip to main content
Glama
Pavelsiba

yandex-direct-mcp-plus

by Pavelsiba

Управление аудиторными целями

set_audience_targets
Destructive

Add, suspend, resume, delete, or change bids on Yandex.Direct audience targets to manage retargeting and interest-based targeting conditions.

Instructions

Добавить, остановить, возобновить, удалить аудиторные цели или изменить их ставки.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bidsNoНовые ставки и приоритеты; обязателен при action=set_bids
actionYesЧто сделать: add, set_bids, suspend, resume или delete (необратимо)
targetsNoУсловия для добавления; обязателен при action=add
audience_target_idsNoУсловия для suspend, resume или delete

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.6.1

TDQS

B3.3/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=true, and openWorldHint=true, so the agent already knows this is a mutating, destructive, external-facing tool. The schema description for the 'delete' action notes it is irreversible ('необратимо'), which adds useful context beyond annotations. However, the description itself says nothing about permissions, rate limits, or side effects — it merely restates the action set.

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?

A single efficient sentence listing the allowed actions. It is front-loaded and wastes no words, though it is extremely terse and arguably could not be shorter without losing the action enumeration.

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

Completeness2/5

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

For a mutation tool with destructive and open-world annotations, no output schema, and complex conditional parameter requirements (bids vs targets vs audience_target_ids depending on action), the description is almost absent. It does not explain action-parameter relationships, does not mention that some actions are irreversible beyond the schema note, and provides no behavioral context for a potentially high-impact operation.

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 description coverage is 100%. Every parameter, nested field, and enum is fully documented in the schema, including when each array is required (add requires targets; set_bids requires bids). The one-sentence description adds no parameter meaning. Baseline 3 is appropriate when the schema does all the work.

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 states specific verbs (add, suspend, resume, delete, change bids) and the resource (аудиторные цели / audience targets). It clearly identifies the tool's operations, but does not differentiate it from base targeting — a reasonable inference is that this is a CRUD/bid-set tool for audience targeting. Sibling list_audience_targets is the read counterpart; no explicit disambiguation is needed but the description doesn't name it.

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 implies when to use the tool (when you need to modify audience targets) but gives no explicit when-not or alternatives. The action enum in the schema effectively lists the operations, but the description adds no routing guidance beyond what the parameter already conveys.

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