Klarix Intelligence Engine

Head-to-head: us vs them (matrix + talk tracks + displacement plan)

analyze_head_to_head

Read-only

Compare YOUR company against a specific competitor or incumbent you want to displace. Researches both sides on the live public web, then returns asymmetric advantages (where you win structurally), their defensive moats (where to stop arguing), a fixed four-dimension comparison matrix (Pricing, Tech / Delivery Speed, Quality Floor, Support / Customization), spoken talk tracks and landmines for a live evaluation, and a three-step displacement strategy. Identify your side with our_domain, our_company_name, or a Klarix client_id. Any claimed advantage the evidence does not support is reported back rather than repeated.

Input Schema

TableJSON Schema

Name	Required	Description
`client_id`	No	Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
`our_domain`	No	Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
`target_domain`	Yes	The competitor or incumbent vendor you are trying to displace, e.g. "zoominfo.com".
`our_advantages`	No	Advantages you believe you hold, in your words. Merged with our_differentiators; the analysis tests them against the evidence rather than accepting them.
`target_vertical`	No	The buying market this head-to-head is aimed at, e.g. "medical device OEMs". Sharpens every talk track.
`our_company_name`	No	Your company name. Curates the analysis toward how YOU win instead of a generic read.
`our_differentiators`	No	What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.
`target_company_name`	No	Proper name of the target, when the domain does not make it obvious.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`sources`	Yes
`verdict`	Yes
`unknowns`	Yes
`landmines`	Yes
`our_domain`	No
`our_context`	No
`talk_tracks`	Yes
`their_moats`	Yes
`win_posture`	Yes
`figure_check`	Yes
`target_domain`	Yes
`our_positioning`	Yes
`target_vertical`	Yes
`our_company_name`	Yes
`comparison_matrix`	Yes
`confidence_detail`	No
`target_positioning`	Yes
`evidence_confidence`	Yes
`target_company_name`	Yes
`claims_not_supported`	Yes
`asymmetric_advantages`	Yes
`displacement_strategy`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 6, 2026

addedOutput schema / properties / figure_check

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "checked": {
+      "type": "number"
+    },
+    "problems": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "evidence": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "figure": {
+            "type": "string"
+          },
+          "found_in": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "status": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "figure",
+          "status",
+          "found_in",
+          "evidence"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "verified": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "checked",
+    "verified",
+    "problems"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "our_company_name",
-  "our_positioning",
-  "target_company_name",
-  "target_domain",
-  "target_positioning",
-  "target_vertical",
-  "verdict",
-  "win_posture",
-  "asymmetric_advantages",
-  "their_moats",
-  "comparison_matrix",
-  "talk_tracks",
-  "landmines",
-  "displacement_strategy",
-  "claims_not_supported",
-  "unknowns",
-  "evidence_confidence",
-  "sources"
-]New value: +[
+  "our_company_name",
+  "our_positioning",
+  "target_company_name",
+  "target_domain",
+  "target_positioning",
+  "target_vertical",
+  "verdict",
+  "win_posture",
+  "asymmetric_advantages",
+  "their_moats",
+  "comparison_matrix",
+  "talk_tracks",
+  "landmines",
+  "displacement_strategy",
+  "claims_not_supported",
+  "figure_check",
+  "unknowns",
+  "evidence_confidence",
+  "sources"
+]

First observedSep 4, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=true, openWorldHint=true), the description discloses that it researches the live public web, tests claimed advantages against evidence rather than accepting them, and reports unsupported claims back instead of repeating them. This evidence-verification behavior is genuinely additive and shapes agent expectations about output reliability. It does not explicitly mention non-deterministic results across calls, but idempotentHint=false combined with live public web research covers that implication.

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

Conciseness5/5

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

Three dense sentences front-load the purpose and then compress the deliverable list, identification options, and evidence-honesty behavior into tight parentheticals. Every sentence earns its place, and the structure mirrors how an agent should read it: what it does, what it returns, and how to identify 'us'.

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 complex 8-parameter research tool, the description covers purpose, output composition, side identification, and evidence handling, while the output schema and annotations cover the remaining details. The only notable gap is the absence of explicit differentiation from siblings like generate_displacement_playbook and get_competitor_battlecard, which partially overlap in outputs. Still, the description stands alone well enough to invoke correctly.

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 description coverage is 100%, with every one of the 8 parameters carrying a meaningful description, including client_id override semantics and the our_advantages evidence-testing behavior. The description adds only a small pointer to the identification trio (our_domain, our_company_name, client_id), so the schema carries the parameter burden. A baseline 3 is appropriate given the schema's thorough coverage.

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 opens with a specific verb and resource, 'Compare YOUR company against a specific competitor or incumbent you want to displace', and enumerates a distinctive deliverable set: asymmetric advantages, defensive moats, a fixed four-dimension comparison matrix, talk tracks, landmines, and a three-step displacement strategy. This output list clearly differentiates it from siblings like get_competitor_battlecard and generate_swot_analysis even without naming them.

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 frames a concrete scenario, displacing a specific competitor in a live evaluation with spoken talk tracks and landmines for that event, which tells an agent when this tool is the right choice. It does not explicitly name alternatives or when-not-to-use conditions, but the displace-plus-live-evaluation framing provides clear context. The instruction to identify your side via our_domain, our_company_name, or client_id also orients the agent on which input path to take.

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

All Klarix Intelligence Engine 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?