Skip to main content
Glama

max_ad_report

Read-onlyIdempotent

Compare MAX ad placements by CPM, click/start, lead and order costs, ROAS, profit, ROMI, and conversion confidence intervals. Flags chance gaps and low data; calculator only, no ad account access.

Instructions

Compare ad placements in MAX by real results: CPM, cost per click or bot start, cost per lead and per order, ROAS, profit after ads and ROMI (with margin), conversion with a 95% confidence interval. Says when a difference between channels may be chance and when there is too little data. A calculator only: it does not touch ad accounts or move money.

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": {
      "placements": "<placements>"
    },
    "name": "max_ad_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoAnswer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
eventsNoOptional bot_started updates, {'payload': …} objects or payload strings; starts are counted per placement id
campaignNoOnly count payloads of this campaign
min_ordersNoBelow this many orders a placement is flagged as low data
placementsYesPer placement: {name, id?, cost, views?, clicks?, starts?, leads?, orders?, revenue?, margin_pct?}

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/closed-world, and the description adds real value beyond them: it discloses that results include a 95% confidence interval, that it flags when a difference may be chance, and that it warns about insufficient data. The 'does not touch ad accounts or move money' line reinforces the non-destructive profile rather than contradicting it. It stops short of explaining output shape or how the confidence test is computed, so not a 5.

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 sentences, front-loaded with the core action, followed by the statistical caveat and the scope disclaimer. No filler or repetition, though the metric enumeration is dense and could be trimmed without losing selection value.

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?

With no output schema, the description carries the burden of telling the agent what comes back, and it does so by listing the metrics and the caveats (chance, low data). Missing is any sense of the output's structure or how the comparison is presented (per-placement table vs pairwise), which would matter for a 5-parameter analytical tool.

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%, so every parameter is already documented in the schema, and the description adds essentially no parameter-level detail — it does not explain the placement object fields, min_orders behavior, or the events/campaign payload matching beyond what the schema states. Baseline 3 applies; only 'with margin' loosely hints at margin_pct.

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 names a specific verb and resource ('Compare ad placements in MAX') and then enumerates the exact metrics produced (CPM, CPBC, CPL, CPO, ROAS, profit after ads, ROMI, conversion with CI). The closing line 'A calculator only: it does not touch ad accounts or move money' bounds what kind of tool it is, which is the key distinction from siblings that act on accounts.

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?

Usage is only implied: an agent can infer this is the tool for evaluating placement performance, but there is no explicit 'use this when…' statement and no reference to any alternative tool or when-not-to-use condition. It also doesn't say what preconditions the caller must satisfy (e.g. that the caller must supply cost and result data itself rather than the tool fetching it).

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