Skip to main content
Glama

Ad group statistics

group_stats
Read-onlyIdempotent

Get per-group daily and total performance metrics for selected ad groups in a campaign—views, clicks, spend, CTR—for a date range up to 100 days.

Instructions

Per-group statistics for the groups you name in one campaign: a flat array with one entry per ad group ({id, name, paymentModel, campaignType, data[] per day, totalData for the period}). Same metrics as campaign_stats — views (impressions), clicks, ctr, spend, spendBonus, cpm, cpc, video quartiles, vtr — with money in rubles. groupIds is required: this tool narrows, it does not enumerate. The period is inclusive, YYYY-MM-DD, and must span at most 100 days. Returns no campaign-level totals; for every group of a campaign call campaign_stats, which carries the same breakdown. Costs weekly API points; the reply's apiPointBalance is what is left until the quota refills Monday 00:00 UTC, so prefer one wide period over many narrow calls.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateToYesLast day of the period, inclusive (YYYY-MM-DD). Must be >= dateFrom, and the period must not exceed 100 days.
dateFromYesFirst day of the period, inclusive (YYYY-MM-DD).
groupIdsYesAd group ids to report on, e.g. [101, 102]. Required; get them from list_groups, or use campaign_stats for the whole campaign.
campaignIdYesCampaign whose groups are reported. Find ids with list_campaigns.
Behavior5/5

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

Annotations already claim readOnly, openWorld, idempotent, non-destructive. The description goes far beyond by disclosing the return structure (flat array, per-day data, totalData), the inclusive 100-day max period, the 'narrows, does not enumerate' behavior, and the weekly API point cost with the quota refill schedule. There is no contradiction with annotations.

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?

Six dense sentences, each delivering a distinct piece of needed information: return format, metric list, required parameter behavior, period constraints, relationship to campaign_stats, and cost/usage advice. No filler or redundancy, and the most critical purpose is front-loaded.

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?

For a tool with no output schema and 4 required parameters, the description fully compensates: it explains the exact output shape, all returned fields, the metrics included, the money unit, the period rules, the requiredness of groupIds, the alternative for campaign-level totals, and the API cost implications. Nothing necessary is left to guesswork.

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% (baseline 3), and the description adds meaningful context beyond schema: 'groupIds is required: this tool narrows, it does not enumerate' clarifies intent, and the inclusive-period/max-100-days constraint is reinforced alongside cost-based advice on choosing a wide period. This elevates it above the baseline, though not to a 5 since the schema itself already documents each parameter precisely.

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: 'Per-group statistics for the groups you name in one campaign', immediately distinguishing it from campaign-level tools. It further differentiates by detailing the flat array structure and explicitly naming sibling tool alternatives like campaign_stats and list_groups. This is a model of purpose clarity.

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?

Explicit when-to-use and when-not-to-use guidance: 'groupIds is required: this tool narrows, it does not enumerate' and 'Returns no campaign-level totals; for every group of a campaign call campaign_stats, which carries the same breakdown.' It also advises on API cost management, saying 'prefer one wide period over many narrow calls.' This fully equips an agent to choose it correctly.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/A1-x-Tech/mcp-avito-ads'

If you have feedback or need assistance with the MCP directory API, please join our Discord server