Quattr

ai_visibility_drilldown

Read-only

AI answer-engine (ChatGPT/Perplexity/Gemini/AI Mode) citations — NOT Google's on-SERP AI Overviews (use competitive_trends/competitive_overview for those). QWA-parity AI Visibility DRILLDOWN for one tracker. Use for "AI visibility by competitor", "by prompts", "by cited URL", "by intent", "by geography", or "by brand". Returns QWA-facing metrics only: Share of Voice %, Citation %, Citations, Mentions %, Mentions, Positive Sentiment %, and Positive Mentions.

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": {
      "tab": "<tab>",
      "date_range": "<date_range>"
    },
    "name": "ai_visibility_drilldown"
  }
}

Input Schema

Name	Required	Description
`tab`	Yes	AI Visibility drilldown tab to mirror QWA: competitors, prompts, cited_urls, intent, geography, or brand.
`brand`	No	QWA branded filter. Use "All" or omit for all prompts; "Yes" for branded; "No" for non-branded. The brand tab ignores this filter.
`limit`	No	Maximum rows to return; defaults to 200.
`device`	No	Optional device filter. Values are normalized to uppercase, e.g. DESKTOP or MOBILE. Applied on the same tracker-scoped AI visibility reads as country. Overview and citation audit require a tracker. If the underlying data has no device filter, the tool says so and returns no totals.
`intent`	No	Restrict to one search intent, e.g. "Informational" / "Transactional".
`country`	No	Optional country filter, e.g. "USA". Applied on tracker-scoped AI visibility reads (overview, citation audit, competitors, trend, and drilldown). Overview and citation audit require a tracker. The geography drilldown tab groups rows by country instead of filtering them. If the underlying data has no country filter, the tool says so and returns no totals.
`tracker`	No	AI Visibility tracker (unified segment id), e.g. "AI Tracker". If omitted, the only ACTIVE tracker is auto-selected; multiple trackers (or only paused ones) return a picker without querying. A paused tracker (collection stopped on its end date) is honored when named explicitly, and the result carries trackerStatus "paused" — report it as historical, not current.
`platform`	No	Restrict to one AI platform, e.g. "chatgpt" / "gemini" (platform key).
`date_range`	Yes	Explicit date range, e.g. "2026-05-01 to 2026-05-31". Both endpoints are INCLUSIVE — the END day is covered (a 7-day range = 7 days). Quattr weeks run Sunday–Saturday; for "last week" use the most recent complete Sun–Sat span.
`comparison_range`	No	Explicit comparison range for period-over-period, e.g. "2026-04-01 to 2026-04-30". Adds per-row deltas (delta + deltaPct) for the metrics; never changes which rows return (deltas are left-joined onto the selected period).

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 20, 2026

changedInput schema / properties / country / description

Previous value: -"Optional QWA country filter, e.g. \"USA\". For ai_visibility_overview this requires a tracker and reads QWA drilldown-backed client metrics; for ai_visibility_drilldown, the geography tab groups rows by country."New value: +"Optional country filter, e.g. \"USA\". Applied on tracker-scoped AI visibility reads (overview, citation audit, competitors, trend, and drilldown). Overview and citation audit require a tracker. The geography drilldown tab groups rows by country instead of filtering them. If the underlying data has no country filter, the tool says so and returns no totals."

changedInput schema / properties / device / description

Previous value: -"Optional QWA device filter. Values are normalized to QWA uppercase, e.g. DESKTOP or MOBILE. For ai_visibility_overview this requires a tracker."New value: +"Optional device filter. Values are normalized to uppercase, e.g. DESKTOP or MOBILE. Applied on the same tracker-scoped AI visibility reads as country. Overview and citation audit require a tracker. If the underlying data has no device filter, the tool says so and returns no totals."

changedInput schema / properties / tracker / description

Previous value: -"AI Visibility tracker (unified segment id), e.g. \"AI Tracker\". If omitted, the only tracker is auto-selected; multiple trackers return a picker."New value: +"AI Visibility tracker (unified segment id), e.g. \"AI Tracker\". If omitted, the only ACTIVE tracker is auto-selected; multiple trackers (or only paused ones) return a picker without querying. A paused tracker (collection stopped on its end date) is honored when named explicitly, and the result carries trackerStatus \"paused\" — report it as historical, not current."

First observedOct 19, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the description's job is to add context — which it does by stating the tool is tracker-scoped ("for one tracker") and by enumerating the exact return set (SoV %, Citation %, Citations, Mentions %, Mentions, Positive Sentiment %, Positive Mentions). It adds nothing about pagination or the paused/auto-selected-tracker behavior that the schema raises, but the added output detail is real value.

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?

Four front-loaded sentences with no filler: identity first, disambiguation second, use cases third, return set last. Slightly discounted because unexplained jargon ("QWA-parity", "QWA-facing") consumes space without adding meaning for an agent unfamiliar with the internal term.

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 10 parameters and no output schema, the description carries real weight and does cover the return metrics and the single-tracker scope. It stops short of mentioning period-over-period delta behavior from comparison_range or how the geography tab groups rather than filters, which the schema handles but which an agent would benefit from seeing at the description level.

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 the schema already documents all 10 parameters — including the tab enum values, brand filter, date-range inclusivity, and comparison_range deltas. The description's "by cited URL / by geography / by brand" phrasing merely restates enum members and adds no syntax or edge-case guidance beyond the schema, which is the baseline-3 case.

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?

It states a specific verb/resource — an AI-visibility DRILLDOWN that returns citation and sentiment metrics for one tracker, enumerating the six breakdown dimensions. It explicitly separates itself from Google on-SERP AI Overviews tools (competitive_trends/competitive_overview), but never distinguishes itself from its closest siblings ai_visibility_overview, ai_visibility_competitors, or ai_visibility_citation_audit, so the agent still has to guess which AI-visibility tool to pick.

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

Usage Guidelines4/5

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

Usage is well signposted: "Use for 'AI visibility by competitor', 'by prompts', 'by cited URL', 'by intent', 'by geography', or 'by brand'," and the negative case is routed explicitly ("NOT Google's ... AI Overviews (use competitive_trends/competitive_overview for those)"). The gap is that the drilldown-vs-overview-vs-competitors decision inside the AI visibility family is never addressed.

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

All Quattr tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?