Ranksmile

Pages AI answers cite

visibility__sources

Read-onlyIdempotent

The pages (by: "url") or sites (by: "domain") the latest scan's AI answers cite, most cited first, each with its type (UGC, Editorial, Reference, Institutional, Corporate, Competitor, You, Other). Per page: whether the answers citing it name the brand, whether the page itself does, and the brands named instead. gap: true marks pages that help competitors and not the brand: Editorial ones are outreach targets, UGC ones community threads, Competitor ones show what to out-write.

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": {
      "workspace_id": "<workspace_id>"
    },
    "name": "visibility__sources"
  }
}

Input Schema

Name	Required	Description
`by`	No	Default url.
`limit`	No	Max rows, 1-100 (default 25).
`offset`	No	Rows to skip (default 0). Keep paging while has_more is true.
`gap_only`	No	Pages only: keep the gap pages. Default false.
`workspace_id`	Yes	From workspace__list.

Output Schema

Name	Required	Description
`by`	Yes
`rows`	Yes	url: url, domain, type, title (the page's own once read, else the one the answer gave), http_status, times_cited, models, answer_names_brand, page_names_brand (null until read), brands_named, gap. domain: domain, type, used (% of answers citing it), citations.
`domain`	Yes
`has_more`	Yes
`type_shares`	Yes	Each type's share (%) of all citations: type, share, citations.
`workspace_id`	Yes
`distinct_domains`	Yes	Distinct sites cited: under 5 is a narrow source base.
`scan_finished_at`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover the read-only/idempotent/non-destructive profile, so the description's job is added context: it discloses ordering (most cited first), the seven-value type taxonomy, the per-page brand-mention signals, and the semantics of gap pages. It does not mention scan freshness, empty-result behavior, or rate limits.

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 primary noun and ordering, then the field detail, then gap semantics — a sensible information hierarchy. The second half is a dense clause chain (three parallel 'whether' clauses plus the gap sentence) that is harder to parse than it needs to be.

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 an output schema present, return-shape explanation is redundant, and the description usefully covers ordering, taxonomy, and gap interpretation instead. Minor gaps remain around what 'latest scan' means temporally and what an empty result signifies.

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 a 3 would be the floor, but the description genuinely adds meaning beyond the schema: it explains that gap_only surfaces pages helping competitors and not the brand and what each resulting type means. The enum for by is also reinforced with intent rather than just 'Default url.'

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 resource with scope: pages/sites cited by the latest scan's AI answers, with the aggregation mode named (by url vs by domain). It is clearly distinguishable from visibility__overview and visibility__prompt, which cover different slices of the same visibility data.

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 description tells the agent how to act on results — Editorial gap pages are outreach targets, UGC ones community threads, Competitor ones show what to out-write — and implies when gap_only matters. It stops short of explicitly naming when to reach for visibility__overview or visibility__prompt instead.

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

All Ranksmile 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?