CrunchJunkie

get_citations

Read-only

Which domains AI engines cite when answering this project's prompts, over a window: per domain the runs that cited it and the runs that only retrieved it during search (where the provider exposes that split; legacy runs without it are reported separately), its share of chats, its category, and its top pages. Returns the most cited domains first: limit sets how many (default 25) and topPages how many pages each (default 1, max 5); summary: true or topPages: 0 drops the pages. totalDomains, runsAnalyzed and shareOfChatsAnswers cover every domain in the window, and domainsReturned says how many rows came back. Filters: days, model, promptId. How cited, retrieved, legacy and share of chats are defined arrives in howToRead and note.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_citations"
  }
}

Input Schema

Name	Required	Description
`days`	No	Window in days (default 30, max 180).
`limit`	No	Domains returned, most cited first (default 25, max 100). Totals cover every domain.
`model`	No	Filter to one engine (a channel id such as grok-3, or its label): every model id behind it counts, Peec AI rows included.
`summary`	No	true = the totals and the domain list without top pages.
`clientId`	No	Client id — uses the AI-Visibility project its Overview opens in the app (the newest).
`promptId`	No	Filter to one prompt.
`topPages`	No	Top pages per domain (default 1, max 5); 0 leaves the pages out, like summary.
`projectId`	No	AI-Visibility project id.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 24, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

removedInput schema / additionalProperties
```
Removed value: -false
```

Changed1 schema field changedOct 24, 2026

changedInput schema / properties / topPages / description

Previous value: -"Top pages per domain (default 1, max 5)."New value: +"Top pages per domain (default 1, max 5); 0 leaves the pages out, like summary."

Changed3 schema fields changedOct 22, 2026

addedInput schema / properties / limit

Added value: +{
+  "description": "Domains returned, most cited first (default 25, max 100). Totals cover every domain.",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / summary

Added value: +{
+  "description": "true = the totals and the domain list without top pages.",
+  "type": "boolean"
+}

addedInput schema / properties / topPages

Added value: +{
+  "description": "Top pages per domain (default 1, max 5).",
+  "maximum": 5,
+  "minimum": 0,
+  "type": "integer"
+}

First observedOct 19, 2026

TDQS

A4/5.0

Behavior5/5

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

Annotations only cover the read-only safety profile, and the description adds a lot beyond that: the cited-vs-retrieved distinction, that legacy runs without the split are reported separately, that totals cover the whole window while domainsReturned reflects the limited rows, and that summaries omit pages. The direction of sorting and the ways to trim output are also disclosed.

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?

The purpose is front-loaded, followed by output shape, then knobs and filters in a logical order. It is dense but nearly every clause carries information; a few default values repeat what the schema already states.

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 return-value burden and does so by naming totalDomains, runsAnalyzed, shareOfChatsAnswers and domainsReturned. It defers the definitions of cited, retrieved, legacy and share of chats to the howToRead and note response fields, which leaves a small gap for an agent that must interpret those terms before calling.

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, and the description adds the key interactions the schema doesn't: limit caps rows while totals still cover every domain, and either `summary: true` or `topPages: 0` suppresses pages. It does restate defaults already present in the schema, so it isn't a full 5.

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?

The description defines a specific verb and resource: it lists the domains AI engines cite when answering this project's prompts over a window and includes per-domain cited/retrieved breakdowns. It is clear enough to stand apart from single-URL and lifetime siblings, but it never names those siblings or says which to prefer.

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 implied by the framing ('which domains ... cite ... over a window') and the filter list (days, model, promptId) signals available scoping. But there is no statement of when to choose this instead of get_cited_url, list_citation_lifetimes or get_ai_attribution, and no exclusions.

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

All CrunchJunkie 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?