Skip to main content
Glama

SearchLink

by com.namubase.searchlink
OverviewDiscussionsAdmin

Am I in AI answers?

ai_visibility
Read-only

Asks Gemini with Google Search each question the user wrote (how their customers would ask an AI) several times, and reports how often the site is cited or named, and which sites the AI cites instead. Asking more than once is what makes the result trustworthy: AI answers vary run to run. The questions must be in the user's own words; Search Console data is never sent to the AI. Use for "do AI answers recommend me?" questions. Results are kept for a week. Starter plan and up.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
runsNoHow many times to ask each question. More runs, steadier numbers. Default 3.
siteYesThe site to read. Accepts "example.com", "https://example.com/" or "sc-domain:example.com"; a subdomain like "blog.example.com" narrows a domain property to that subdomain. Call list_sites if unsure.
questionsYes1 to 8 questions in the user's own words, the way a customer would ask ChatGPT or Google AI, e.g. "best plumber in Austin for a burst pipe". Ask the user for them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / queries
      Removed value: -{
-  "default": 5,
-  "description": "How many of the site's top non-brand searches to check, 1 to 8. Default 5.",
-  "maximum": 8,
-  "minimum": 1,
-  "type": "integer"
-}
    • addedInput schema / properties / questions
      Added value: +{
+  "description": "1 to 8 questions in the user's own words, the way a customer would ask ChatGPT or Google AI, e.g. \"best plumber in Austin for a burst pipe\". Ask the user for them.",
+  "items": {
+    "maxLength": 200,
+    "minLength": 3,
+    "type": "string"
+  },
+  "maxItems": 8,
+  "minItems": 1,
+  "type": "array"
+}
    • changedInput schema / required
      Previous value: -[
-  "site"
-]New value: +[
+  "site",
+  "questions"
+]
  2. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond that: repeated runs are required for trustworthy numbers because AI answers vary, results are retained for a week, Search Console data is never sent to the AI, and a plan tier is required. It does not discuss latency or cost of multiple runs.

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 core action is front-loaded in the first sentence, followed by the rationale, constraints, and eligibility. Sentences are dense but each carries information (variance, retention, privacy, plan). Slightly long for a three-parameter tool, but nothing is filler.

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 burden and does state the return shape in prose (citation frequency and the sites the AI cites instead). Combined with the retention window and plan gating, an agent has enough to call it correctly; only the ai_citations relationship and any latency expectations are unaddressed.

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 schema already documents site, questions, and runs with formats and limits. The description still adds meaning by explaining *why* runs matters (variance makes single runs untrustworthy) and why questions must be verbatim user phrasing rather than invented keywords.

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 states a concrete verb and resource: it asks Gemini with Google Search each user-written question repeatedly and reports citation/mention frequency plus competing cited sites. An agent can grasp exactly what the tool produces. It does not, however, distinguish itself from the close sibling ai_citations, which an agent might confuse it with.

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 gives an explicit use case ("do AI answers recommend me?" questions) plus prerequisites: questions must be in the user's own words, and "Starter plan and up" gates access. It stops short of naming alternatives or exclusions relative to ai_citations, so an agent gets context but no routing guidance between the two citation-oriented tools.

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

All SearchLink toolsInspect
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