Ranksmile

AI visibility

visibility__overview

Read-onlyIdempotent

How often AI answers (ChatGPT, Perplexity, Gemini, Google AI) name this workspace's brand in the latest scan: the brand score, the brands named instead, the score per topic, the trend over the last scans, and every tracked prompt with its intent, tags, per-engine score and mention rate, least-mentioned first. The prompts at 0 are the gaps content can close; visibility__prompt shows why one is lost. The site-wide parts (overview, competitors, topics, history, scans_total, unanswered_prompts) come on the first page only; later pages carry the next prompts.

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__overview"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max rows, 1-100 (default 20).
`offset`	No	Rows to skip (default 0). Keep paging while has_more is true.
`workspace_id`	Yes	From workspace__list.

Output Schema

Name	Required	Description
`brand`	Yes
`domain`	Yes
`topics`	No	First page only. Per topic, weakest first: topic, prompts, mention_rate, previous_mention_rate (the scan before; null when none or not asked then), visibility_score.
`history`	No	First page only. Last completed scans, oldest first: scan_id, finished_at, visibility_score, mention_rate (null while a scan is still extracting brands).
`prompts`	Yes	Tracked prompts, least-mentioned first: prompt_id, topic, intent (informational\|commercial\|transactional\|null), tags, text, mention_rate, previous_mention_rate (the scan before; null when none or not asked then), avg_position, per_model (model, score), brands_named.
`has_more`	Yes
`overview`	No	First page only. visibility_score (0-100), mention_rate (% of answers naming the brand), avg_position, per_model. Null before the first scan.
`competitors`	No	First page only. Brands the answers name in at least two answers, plus every competitor the user tracks (listed first, tracked: true): brand, domain, mention_rate, avg_position, visibility_score, tracked.
`scans_total`	No	First page only. Completed scans of this site so far.
`workspace_id`	Yes
`scan_finished_at`	No
`unanswered_prompts`	No	First page only. Prompts every engine failed to answer in this scan, so they have no rate: prompt_id, topic, text. visibility__prompt shows the errors.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description adds non-obvious traits instead: the site-wide sections (overview, competitors, topics, history, scans_total, unanswered_prompts) appear on the first page only while later pages carry prompts, and prompts are ordered least-mentioned first. Paging/first-page semantics is exactly the kind of detail annotations cannot express.

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 core purpose and paging caveat, with no filler or marketing language. It runs long and restates data the output schema already describes, which slightly dilutes density, but every clause carries signal.

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?

Given an output schema is present, explaining return values is optional; the description instead covers what the schema cannot — paging split between first and later pages, prompt ordering, and the drill-down path to visibility__prompt. Nothing needed to invoke it correctly 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. The description nonetheless clarifies what offset actually pages over (prompts, once the site-wide block has been consumed), which changes how an agent interprets limit/offset beyond the schema's 'Rows to skip' wording.

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?

The description gives a specific verb and resource — 'how often AI answers name this workspace's brand in the latest scan' — and enumerates the payload (brand score, competitor brands, per-topic scores, trend, tracked prompts). It is clearly distinguishable from sibling visibility__prompt (per-prompt drill-down) and visibility__sources.

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?

It signals when to stay on this tool versus drilling down: 'The prompts at 0 are the gaps content can close; visibility__prompt shows why one is lost.' That is a clear routing rule, but it does not state when NOT to use this tool (e.g. for engines not in the scan, or for a different workspace scope).

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?