Innovalyxx Sovereign Edge

Agent / site visibility snapshot

get_agent_visibility

Read-onlyIdempotent

Retrieve a 0–100 derived visibility score and estimated LLM mention rate for a URL. Not independently verified. Compliance: EU AI Act Art. 50, schema.org. Cost $0.01 per call. Not HTTP uptime, TLS, or a credit.

Input Schema

Name	Required	Description	Default
`url`	Yes	Absolute HTTPS URL whose generative-engine visibility score and estimated LLM mention rate should be returned.

Output Schema

Name	Required	Description
`ok`	No	True when the tool completed without a validation error.
`url`	No	Queried URL.
`tool`	No	Tool name that produced this payload.
`payment`	No	Settlement receipt after x402 or sandbox payment.
`geo_score`	No	DERIVED 0–100 generative-engine visibility score. Not independently verified.
`verification_outcome`	No	INDETERMINATE until a separate verifier records PASS or FAIL.
`result_classification`	No	DERIVED for this score. Settlement does not make it verified.
`estimated_llm_mention_rate`	No	DERIVED estimated LLM mention rate. Not a live observation of LLM answers.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 24, 2026

changedOutput schema / description

Previous value: -"Generative-engine visibility snapshot (geo_score and estimated_llm_mention_rate)."New value: +"Derived generative-engine visibility snapshot. geo_score and estimated_llm_mention_rate are estimates, not an independent verification or a live observation of LLM answers."

changedOutput schema / properties / estimated_llm_mention_rate / description

Previous value: -"Estimated LLM mention rate for the URL."New value: +"DERIVED estimated LLM mention rate. Not a live observation of LLM answers."

changedOutput schema / properties / geo_score / description

Previous value: -"0–100 generative-engine visibility score."New value: +"DERIVED 0–100 generative-engine visibility score. Not independently verified."

addedOutput schema / properties / result_classification

Added value: +{
+  "description": "DERIVED for this score. Settlement does not make it verified.",
+  "type": "string"
+}

addedOutput schema / properties / verification_outcome

Added value: +{
+  "description": "INDETERMINATE until a separate verifier records PASS or FAIL.",
+  "type": "string"
+}

Changed4 schema fields changedSep 17, 2026

changedInput schema / properties / url / description

Previous value: -"Absolute HTTPS URL to check for HTTP status, TLS validity, response time, and site score."New value: +"Absolute HTTPS URL whose generative-engine visibility score and estimated LLM mention rate should be returned."

changedOutput schema / description

Previous value: -"URL health / site-score snapshot (HTTP, TLS, response time, 0-100 score)."New value: +"Generative-engine visibility snapshot (geo_score and estimated_llm_mention_rate)."

changedOutput schema / properties / estimated_llm_mention_rate / description

Previous value: -"Deterministic mention-rate estimate."New value: +"Estimated LLM mention rate for the URL."

changedOutput schema / properties / geo_score / description

Previous value: -"0-100 site score from HTTP + local weights."New value: +"0–100 generative-engine visibility score."

Changed3 schema fields changedSep 17, 2026

changedInput schema / properties / url / description

Previous value: -"Merchant URL whose estimated LLM mention rate and GEO score should be returned."New value: +"Absolute HTTPS URL to check for HTTP status, TLS validity, response time, and site score."

changedOutput schema / description

Previous value: -"Estimated agent-visibility metrics for a URL."New value: +"URL health / site-score snapshot (HTTP, TLS, response time, 0-100 score)."

changedOutput schema / properties / geo_score / description

Previous value: -"Latest stored GEO score, if any."New value: +"0-100 site score from HTTP + local weights."

First observedSep 13, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the bar is lower. The description adds genuinely new context: the score is 'derived' and 'not independently verified' (an important trust caveat), and it discloses a $0.01 per-call cost, which matters for cost-aware agents. It stops short of explaining freshness, score derivation method, or failure modes.

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 deliverable in one sentence, then caveats and cost. Zero filler. The trailing 'Compliance: EU AI Act Art. 50, schema.org' is terse to the point of ambiguity and slightly dilutes an otherwise tight definition.

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?

An output schema exists, so return-shape explanation is unnecessary, and annotations cover the safety profile. The description supplies the remaining essentials an agent needs — cost, trust caveat, and scope exclusions — though it omits freshness/refresh behavior and any guidance on when a different visibility/maturity tool is the better call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single 'url' parameter is fully documented in the schema, so the description only echoes it as 'for a URL'. Baseline 3 applies; no added syntax, format, or constraint detail beyond the schema's 'Absolute HTTPS 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 verb (Retrieve) and a concrete resource (0–100 derived visibility score plus estimated LLM mention rate for a URL). The explicit negative scoping — 'Not HTTP uptime, TLS, or a credit' — separates it from adjacent concepts an agent might confuse it with, including siblings like verify_site_certification or get_agent_maturity.

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?

It rules out several misreadings (uptime, TLS, credit) which is a partial when-not, but it never states a positive when-to-use scenario or names an alternative sibling for adjacent questions. The agent must infer usage from the resource description alone.

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

All Innovalyxx Sovereign Edge 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?