Citation Intelligence MCP

competitors_compete

Read-onlyIdempotent

Benchmark your URL against AI-cited competitors for a search query. Returns your citation score, average competitor score, and the gap.

Instructions

End-to-end competitive snapshot for a single query. Calls check_citations to get the cited URLs, then runs compare_domains on your_url vs the top cited competitors. Returns your score, the average competitor score, and the gap.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	Search query to test (what would a user ask an AI?).
`engine`	No	AI engine to query for the citation set. 'auto' picks the first available key.	auto
`your_url`	Yes	Your URL to benchmark against the cited competitors.
`max_competitors`	No	How many cited URLs to compare against your_url. Capped at 9 (compare_domains accepts max 10 URLs total including yours).

Output Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	The query that was tested.
`engine`	Yes	Engine used for the citation fetch.
`your_url`	Yes	Your URL that was benchmarked.
`score_gap`	Yes	your_score minus average_competitor_score.
`comparison`	Yes	Full compare_domains result.
`fetched_at`	Yes	UTC ISO-8601 timestamp.
`your_score`	Yes	predict_citation score for your URL (null on error).
`competitors`	Yes	Competitor URLs that were compared.
`your_in_citations`	Yes	Whether your URL appeared in the engine's citation list.
`average_competitor_score`	Yes	Mean score across competitor URLs.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.1.2Oct 2, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds genuine behavioral value by disclosing that this triggers two sequential sub-calls and summarizing the returned aggregate (your score, competitor average, gap), which implies latency/cost characteristics.

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?

Three tight sentences: the deliverable first, the call sequence second, the return shape third. No filler and nothing buried.

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 a full parameter schema, rich annotations, and an output schema, the description only needs to explain the composite behavior and it does. Minor gap: it doesn't hint at engine/failure behavior when a sub-call like check_citations has no key available, but that is largely covered by the 'auto' schema note.

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% and every parameter (query, engine, your_url, max_competitors) is documented in the schema, including the enum and the max-9 cap nuance. The description adds no parameter-level detail beyond what the schema already provides, so the baseline 3 applies.

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 deliverable ('end-to-end competitive snapshot for a single query') and names the exact sub-tools it orchestrates (check_citations, compare_domains), which distinguishes it from the plain single-purpose siblings like competitors_compare and citations_check.

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?

The pipeline description makes the usage context clear: use it when you want a one-shot competitive snapshot rather than stitching the two underlying calls yourself. It doesn't state an explicit when-not or name the sibling to use instead, so it falls short of a 5.

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