Generect

Enrich one company

enrich_company

Full profile for one known company, by Generect id, LinkedIn URL, domain or name. Billable: about $0.02 per record found (not-found is refunded) at the Tier 0 list price. Accounts can pay a different rate: get_balance returns this account's prices, and every response reports what was actually spent in cost.amount_charged_usd. Not found costs nothing. Domain is the most reliable identifier after id; name matching is fuzzy.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "enrich_company"
  }
}

Input Schema

Name	Required	Description
`id`	No	Generect company id.
`mode`	No	Data mode. "database" = Generect's own index: sub-second, free counts, free thin rows (see detail) or cheaper full rows; it accepts a subset of the filters today and names any it rejects. "realtime" = live LinkedIn lookup, 5–60s, billed per row, accepts every realtime filter. "auto" (default) tries database first and escalates to realtime only if a filter you passed is rejected there (the escalation is reported, and is refused above the per-call spend ceiling). Pick "database" explicitly when a recent cached record is good enough and cost matters more than freshness.
`name`	No	Company name (fuzzy match).
`domain`	No	Company domain without protocol, e.g. "stripe.com".
`compact`	No	Default true: return a small per-company summary (including the Generect `id`, which every later step accepts). Set false for the full raw record (~80 fields), only worth it when you specifically need skills, education or other deep fields.
`timeout_ms`	No	Request timeout in milliseconds.
`linkedin_url`	No	LinkedIn company page URL.

Output Schema

Name	Required	Description	Default
`cost`	No
`lead`	No
`mode`	No
`found`	No
`company`	No
`test_mode`	No
`test_mode_notice`	No
`vocabulary_warnings`	No
`deprecated_params_ignored`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 9, 2026

changedInput schema / properties / compact / description

Previous value: -"Default true: return a small per-company summary (including the Generect `id`, which every later step accepts). Set false for the full raw record (~80 fields) — only worth it when you specifically need skills, education or other deep fields."New value: +"Default true: return a small per-company summary (including the Generect `id`, which every later step accepts). Set false for the full raw record (~80 fields), only worth it when you specifically need skills, education or other deep fields."

Changed5 schema fields changedOct 7, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

removedInput schema / additionalProperties
```
Removed value: -false
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / properties / deprecated_params_ignored / propertyNames
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / vocabulary_warnings / items
```
Added value: +{}
```

Changed1 schema field changedOct 6, 2026

changedInput schema / properties / mode / description

Previous value: -"Data mode. \"database\" = cached, sub-second, cheaper, free counts, core filters only. \"realtime\" = live LinkedIn lookup, 5–60s, pricier, supports every filter. \"auto\" (default) tries database first and only escalates to realtime if a filter you passed is unsupported there — an escalation is reported in the response. Pick \"database\" explicitly when a recent cached record is good enough and cost matters more than freshness."New value: +"Data mode. \"database\" = Generect's own index: sub-second, free counts, free thin rows (see detail) or cheaper full rows; it accepts a subset of the filters today and names any it rejects. \"realtime\" = live LinkedIn lookup, 5–60s, billed per row, accepts every realtime filter. \"auto\" (default) tries database first and escalates to realtime only if a filter you passed is rejected there (the escalation is reported, and is refused above the per-call spend ceiling). Pick \"database\" explicitly when a recent cached record is good enough and cost matters more than freshness."

Changed1 schema field changedSep 24, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "company": {},
+    "cost": {
+      "additionalProperties": false,
+      "properties": {
+        "amount_charged_usd": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "billed": {
+          "type": "string"
+        },
+        "note": {
+          "type": "string"
+        },
+        "operation": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "deprecated_params_ignored": {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "found": {
+      "type": "boolean"
+    },
+    "lead": {},
+    "mode": {
+      "type": "string"
+    },
+    "test_mode": {
+      "type": "boolean"
+    },
+    "test_mode_notice": {
+      "type": "string"
+    },
+    "vocabulary_warnings": {
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

AddedSep 10, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations only mark this as non-read-only, open-world and non-destructive; the description goes well beyond them with concrete cost (~$0.02/record, not-found refunded, per-account pricing via get_balance, actual spend in cost.amount_charged_usd), latency (5–60s realtime) and a per-call spend ceiling. That is exactly the kind of billing/rate context annotations cannot convey.

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?

Cost and identifier selection are front-loaded and every sentence carries information. There is minor redundancy in stating refund behavior twice ("not-found is refunded" and "Not found costs nothing"), which keeps it just short of ideal.

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 and annotations thin, the description fills the important gaps—price, refunds, latency, mode escalation, and which identifier to trust. It does not state that at least one identifier must be supplied (required list is empty) or any authentication/Tier precondition, which leaves a small hole for an agent calling it blind.

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, but the description adds genuine meaning: an identifier reliability ranking (id > domain > fuzzy name) and the fact that compact=true returns the Generect id that later steps accept. The mode and timeout parameters are left to the schema, which is adequate.

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 gives a specific verb+resource ("Full profile for one known company") and enumerates accepted identifiers (id, LinkedIn URL, domain, name). The word "known" implicitly separates it from a search tool, but no sibling such as search_companies or enrich_lead is named, so the differentiation is inferred rather than explicit.

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 supplies real selection guidance: prefer id, then domain, and treat name as fuzzy; set compact=false only when deep fields are needed; pick mode=database when a cached record is acceptable and cost matters. What is missing is an explicit statement of when to use a different tool (e.g. search_companies) instead of this one.

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

All Generect 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.