Citation Intelligence MCP

report_visibility

Idempotent

Generate an AI visibility report for a domain across a set of queries, measuring citation rate, share of voice, average rank, and brand sentiment. Outputs a Markdown report.

Instructions

Turnkey AI visibility report for a domain across a query set. Composes check_citations over every query (or a saved panel) and returns the metrics AI-visibility trackers sell as a dashboard, in one call: mention frequency (citation_rate), share_of_voice vs competitors, average rank when cited, and brand sentiment from the answer text. Side effects: one check_citations call per query (costs API quota for uncached queries; cached queries are free). Returns structured summary + top_domains + per_query, plus a rendered Markdown report (include_markdown=true) suitable for a public page. Provide queries[] or a panel name. Same engine selection as check_citations.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`panel`	No	Name of a saved panel (see panel_track) to pull queries from. Provide this OR `queries`.
`domain`	Yes	The domain you are measuring visibility for (e.g. automatelab.tech).
`engine`	No	AI engine to query. 'auto' picks the first configured key. Same selection as check_citations.	auto
`queries`	No	Queries to run. Provide this OR `panel`. Each is sent to the AI engine via check_citations.
`brand_terms`	No	Brand name variants to detect in answer text for sentiment (defaults to the domain's second-level label).
`competitors`	No	Optional competitor domains to surface explicitly in the share-of-voice table.
`max_results`	No	Max citations to pull per query.
`include_markdown`	No	If true (default), include a rendered Markdown report under `markdown`.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No
`summary`	Yes
`markdown`	No	Rendered Markdown report. Present when include_markdown=true.
`per_query`	Yes
`top_domains`	Yes	Share-of-voice table, most-cited domains first.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.1.2Oct 2, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Discloses concrete side effects beyond the annotations: one check_citations call per query, API quota cost for uncached queries with cached queries free. It also states the return shape (summary + top_domains + per_query + optional markdown), which the annotations alone don't convey.

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?

Front-loaded with the purpose before the mechanics, and every sentence carries information (metrics list, side effects, inputs, return shape). It is dense and somewhat long but with negligible 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?

For a high-complexity aggregation tool with an output schema already present, the description covers inputs, cost semantics, and the composed-call behavior needed to invoke it correctly. Nothing essential is missing.

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 real meaning: queries[] and panel are mutually exclusive alternatives, brand_terms defaults to the domain's second-level label, and engine selection mirrors check_citations. This goes beyond restating the schema.

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 verb and resource ('Turnkey AI visibility report for a domain across a query set') and enumerates exactly what it returns (mention frequency, share_of_voice, average rank, sentiment). It also clarifies its relationship to check_citations by describing itself as composing that tool over each query, which distinguishes it from the raw citation siblings.

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 'one call' / 'dashboard' framing implies when to reach for it over individual checks, and it specifies the panel-vs-queries requirement. However, it never explicitly states when NOT to use it or names a sibling alternative (e.g. citations_check, competitors_compare) as the correct choice in a given scenario.

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