Leadgen ONRC Romania

Report missing or wrong data

report_issue

Report to the person who runs Leadgen what is missing or wrong: a missing field, firm or source (kind 'gap'), a wrong company record ('wrong_record', pass its cui), a bug, an idea. Free, never counted as a lookup. contact is optional (an address for a reply); nothing is mailed to it automatically. Registry records are corrected at the source (ONRC) and arrive with the next snapshot.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cui`	No	Optional CUI of the firm the report is about (for 'wrong_record').
`kind`	No	One of 'gap' (a missing field, firm or source; the default), 'wrong_record' (pass its cui), 'bug', 'idea', 'other'.	gap
`contact`	No	Optional email address for a reply; nothing is mailed to it automatically.
`message`	Yes	The report, in plain words: what is missing or wrong.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No	The report's id.
`kind`	No	The kind filed.
`note`	No	For wrong_record: how registry records get corrected.
`error`	No	Set only when there is no answer (empty_query, invalid_cui, data_unavailable, plan_required ...); such a call is not counted.
`status`	No	received.
`message`	No	A sentence for the caller.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 17, 2026

addedInput schema / properties / contact / description

Added value: +"Optional email address for a reply; nothing is mailed to it automatically."

addedInput schema / properties / cui / description

Added value: +"Optional CUI of the firm the report is about (for 'wrong_record')."

addedInput schema / properties / kind / description

Added value: +"One of 'gap' (a missing field, firm or source; the default), 'wrong_record' (pass its cui), 'bug', 'idea', 'other'."

addedInput schema / properties / message / description

Added value: +"The report, in plain words: what is missing or wrong."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "The receipt for the report.",
+  "properties": {
+    "error": {
+      "description": "Set only when there is no answer (empty_query, invalid_cui, data_unavailable, plan_required ...); such a call is not counted.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "id": {
+      "description": "The report's id.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "kind": {
+      "description": "The kind filed.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "message": {
+      "description": "A sentence for the caller.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "note": {
+      "description": "For wrong_record: how registry records get corrected.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "status": {
+      "description": "received.",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}

AddedOct 17, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so safety is covered; the description goes further with real operational context: the report is free and never counted as a lookup, no email is sent to contact automatically, and registry corrections land at the source (ONRC) with the next snapshot. What is missing is who consumes the report or any acknowledgement/timing expectation for non-registry kinds.

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 purpose, then kind taxonomy, then cost and delivery caveats — a sensible order. It is a single dense block with some restatement of schema-documented details (contact behavior appears in both places), so minor trimming is possible.

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 4 params, an output schema present, and 100% schema coverage, the description covers what an agent needs: what to report, which kind to pick, and the cost/behavioural implications. It stops short of describing expected acknowledgement or how the reporter is identified, but no essential calling information is missing.

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%, so the schema already defines cui, kind, contact and message. The description restates those same semantics (kind values, 'pass its cui', contact is optional and not auto-mailed) rather than adding new meaning, so baseline 3 is appropriate.

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 ('Report to the person who runs Leadgen what is missing or wrong') and immediately enumerates the reportable categories (gap, wrong_record, bug, idea). This cleanly separates it from every sibling, all of which are read-only lookups rather than feedback channels.

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?

Gives clear context for each report kind: gaps for missing fields/firms/sources, 'wrong_record' with its cui, plus bug and idea. It doesn't need to name a non-reporting alternative because no sibling does this job, but it also never states any exclusion or precondition beyond the kind semantics.

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

All Leadgen ONRC Romania 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.