Skip to main content
Glama

Sextant Web - Website GEO, SEO, and Analytics

Get AI visibility sources

seo_get_ai_visibility_sources
Read-onlyIdempotent

For a normal review make one run-wide call using the result runId and these top-level arguments (there is no filters object): topic null, engines null, promptId null, cursor null, competitorGap false; never enumerate every engine or prompt. Use engines to request one or more engines in a single filtered call. Read explicit cited pages or domains for the selected run/topic/engines, with ownership, distinct answer/prompt counts, per-engine counts, supporting observation IDs, and valid-answer coverage. Defaults to neutral prompts; request branded=all to include branded diagnostics. Use the same runId and broad filters as results, with competitorGap=false for overall sources. A gap-only source query is a separate subset and must be labeled. Coverage describes the selected run before the gap filter; consult appliedFilters. Pagination and truncation are explicit. Does not crawl URLs or collect answers.

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": {
      "siteId": "<siteId>"
    },
    "name": "seo_get_ai_visibility_sources"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
runIdNoOmit or null for the latest baseline/scheduled run, or the latest manual check when there is none. Reuse the returned runId for related source/answer reads. Do not use the string all.
topicNoOmit or null for all topics in the run. Filter by an exact saved topic name only when requested; do not use the string all.
cursorNoOmit or null for the first page. Use only a returned nextCursor for another page; do not use the string all.
siteIdYesThe Sextant site ID.
brandedNoneutral
enginesNoOmit or null for all engines in one call. Provide one or more engines for an explicitly requested subset, or an empty array for no engines. Do not make separate calls for each engine or use the string all.
groupByNourl
promptIdNoOmit or null for all prompts in the run. Provide an exact prompt ID only when requested; includeHistory returns that prompt's prior observations. Do not use the string all.
ownershipNoall
competitorGapNoUse false for the initial review, overall sources and branded diagnostics. True restricts rows to answers where a competitor appears and your brand is absent; an empty gap subset does not mean answer details are missing.
includeHistoryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description does add real behavioral context beyond that: coverage is computed on the selected run before the gap filter, gap-only subsets must be labeled, pagination and truncation are explicit, and `appliedFilters` should be consulted. That is meaningful, though the density makes the behavioral model hard to absorb in one pass.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is valuable but the structure works against it: the paragraph opens with calling mechanics rather than what the tool returns, and long semicolon-chained clauses ("topic null, engines null, promptId null, cursor null, competitorGap false") make it hard to scan. Nothing is strictly wasted, but the front-loading is wrong for an agent deciding whether to call this tool.

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?

For a 12-parameter tool with no output schema, the description is unusually complete: it describes the returned fields, per-engine counts, coverage semantics, the appliedFilters escape hatch, and pagination/truncation behavior. Minor gaps remain around how the four unexplained parameters interact with the described output shape.

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 58%, so the description must carry weight, and it does: it explains that there is no filters object, that topic/engines/promptId/cursor should be null for a normal review, that `engines` accepts a subset in one call, that competitorGap=true restricts to answers where a competitor appears and your brand is absent, and that branded=all adds diagnostics. The semantics of `groupBy`, `ownership`, `limit`, and `includeHistory` are left entirely to the schema.

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 core statement "Read explicit cited pages or domains for the selected run/topic/engines, with ownership, distinct answer/prompt counts, per-engine counts..." gives a specific verb and resource and enumerates what comes back. However, it is buried mid-paragraph after call-mechanics, and it never explicitly distinguishes this from the sibling answer/results tools beyond a loose "same runId and broad filters as results" reference.

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?

Strong, explicit guidance: make one run-wide call with null filters, use `engines` for a subset instead of fanning out, use competitorGap=false for overall sources and true for the gap subset, and default branded=neutral unless diagnostics are requested. It also states an exclusion ("Does not crawl URLs or collect answers"). It stops short of naming the alternative sibling tools an agent should pick instead when it wants raw answers rather than cited sources.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources