HirePulse MCP

Vendor Stability Check

b2b_vendor_stability_evaluator

Read-only

Assess a B2B vendor's stability before procurement using public technology and hiring evidence, with explicit evidence gaps and unknowns returned for supplier due diligence.

Instructions

Returns structured public evidence and explicit unknowns. Assess a B2B vendor before procurement using public technology and hiring evidence; returns a stability assessment, evidence gaps and limitations. Use for supplier due diligence; use get_company_profile for general company enrichment or pre_purchase_merchant_trust_check for an online shop purchase. Missing history stays unknown, never an invented trend. $0.10 only when a useful assessment is returned.

Input Schema

Name	Required	Description	Default
`context`	No	Optional. A few words on why you are calling this tool. Recorded without your identity to improve the tools; leave out personal data.
`vendor_domain`	Yes	Public domain without scheme, path or port.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv1.0.0Oct 27, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Optional. A few words on why you are calling this tool. Recorded without your identity to improve the tools; leave out personal data.",
+  "type": "string"
+}

changedInput schema / properties / vendor_domain / examples

Previous value: -[
-  "example.com"
-]New value: +[
+  "allbirds.com"
+]

addedOutput schema / anyOf

Added value: +[
+  {
+    "description": "Only status=ok is charged. Diagnostic results may omit result fields; unknown facts are null.",
+    "properties": {
+      "domain": {
+        "type": "string"
+      },
+      "engineering_and_support_headcount_trend": {
+        "type": "string"
+      },
+      "error_reason": {
+        "type": "string"
+      },
+      "hiring_velocity": {
+        "type": "object"
+      },
+      "limitations": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "seo_visibility_trend": {
+        "type": "string"
+      },
+      "stability_status": {
+        "enum": [
+          "GROWING",
+          "STABLE",
+          "CONTRACTING",
+          "HIGH_RISK",
+          "UNKNOWN"
+        ],
+        "type": "string"
+      },
+      "status": {
+        "enum": [
+          "ok",
+          "no_data",
+          "unreachable"
+        ],
+        "type": "string"
+      },
+      "tech_stack_summary": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "vendor_domain": {
+        "type": "string"
+      },
+      "vendor_health_score": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "verified_contacts_available": {
+        "type": [
+          "boolean",
+          "null"
+        ]
+      }
+    },
+    "required": [
+      "domain",
+      "status"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": true,
+    "properties": {
+      "code": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "status": {
+        "maximum": 599,
+        "minimum": 400,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "status",
+      "code"
+    ],
+    "type": "object"
+  }
+]

removedOutput schema / description

Removed value: -"Only status=ok is charged. Diagnostic results may omit result fields; unknown facts are null."

removedOutput schema / properties

Removed value: -{
-  "domain": {
-    "type": "string"
-  },
-  "engineering_and_support_headcount_trend": {
-    "type": "string"
-  },
-  "error_reason": {
-    "type": "string"
-  },
-  "hiring_velocity": {
-    "type": "object"
-  },
-  "limitations": {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "seo_visibility_trend": {
-    "type": "string"
-  },
-  "stability_status": {
-    "enum": [
-      "GROWING",
-      "STABLE",
-      "CONTRACTING",
-      "HIGH_RISK",
-      "UNKNOWN"
-    ],
-    "type": "string"
-  },
-  "status": {
-    "enum": [
-      "ok",
-      "no_data",
-      "unreachable"
-    ],
-    "type": "string"
-  },
-  "tech_stack_summary": {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "vendor_domain": {
-    "type": "string"
-  },
-  "vendor_health_score": {
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "verified_contacts_available": {
-    "type": [
-      "boolean",
-      "null"
-    ]
-  }
-}

removedOutput schema / required

Removed value: -[
-  "domain",
-  "status"
-]

First observedv0.1.0Oct 21, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, yet the description still adds real behavioral context: absent history is reported as unknown rather than inferred, and billing is conditional ('$0.10 only when a useful assessment is returned'). It stops short of describing latency, rate limits, or what evidence sources are actually consulted.

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-loads the return contract and keeps the routing guidance tight. There is mild redundancy between 'Returns structured public evidence and explicit unknowns' and the later 'returns a stability assessment, evidence gaps and limitations', which restates the same idea.

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 an output schema present, return values need not be explained, and the description still covers scope, uncertainty handling, cost, and sibling routing. What remains thin is the evidence base itself (which public signals count as technology/hiring evidence), which would help an agent judge applicability.

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% for both parameters, including the domain format constraint and the opt-in context field, so the schema carries the parameter burden. The description adds nothing about parameter values beyond the implicit notion of a vendor domain, which is the correct baseline here.

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 and resource ('Assess a B2B vendor before procurement using public technology and hiring evidence') and names the artifact returned ('a stability assessment, evidence gaps and limitations'). It is explicitly differentiated from get_company_profile and pre_purchase_merchant_trust_check, so an agent can route without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear use condition ('supplier due diligence') and names two alternatives with the situations that select them (general enrichment, online-shop purchase). The exclusions are concrete rather than implied.

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