numertel

Sprawdź numer telefonu (PL)

check_phone_number

Read-onlyIdempotent

Sprawdź reputację polskiego numeru telefonu. UŻYJ, gdy użytkownik pyta: kto dzwonił, czy numer to spam/oszustwo, czy telefon rzekomo z banku lub urzędu jest prawdziwy. Zwraca operatora z zakresów UKE (z notą o przenośności MNP), etykietę ryzyka z opinii, status w wykazie DNO UKE (połączenie przychodzące z numeru DNO jest sfałszowane — spoofing), wpis z Białej Listy oficjalnych infolinii i liczniki zgłoszeń. Dane: numertel.pl.

Input Schema

Name	Required	Description	Default
`number`	Yes	Polski numer w formacie 9 cyfr, np. 510100100 (akceptowane +48 i spacje — zostaną usunięte)

Output Schema

Name	Required	Description	Default
`url`	Yes
`e164`	Yes
`is_dno`	Yes
`number`	Yes
`dno_note`	No
`operator`	No
`score_avg`	No
`whitelist`	No
`spam_label`	Yes
`attribution`	Yes
`number_type`	No
`operator_note`	No
`sightings_30d`	No
`total_opinions`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 20, 2026

changedOutput schema / properties / spam_label / enum

Previous value: -[
-  "brak_danych",
-  "raczej_bezpieczny",
-  "podejrzany",
-  "niebezpieczny",
-  "dno_spoofing"
-]New value: +[
+  "brak_danych",
+  "raczej_bezpieczny",
+  "zgloszony",
+  "podejrzany",
+  "niebezpieczny",
+  "dno_spoofing"
+]

Changed2 schema fields changedJun 12, 2026

changedInput schema / properties / number / description

Previous value: -"Polski numer: 9 cyfr (np. 500100200). Akceptowane +48 i spacje, zostaną usunięte."New value: +"Polski numer w formacie 9 cyfr, np. 510100100 (akceptowane +48 i spacje — zostaną usunięte)"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "attribution": {
+      "type": "string"
+    },
+    "dno_note": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "e164": {
+      "type": "string"
+    },
+    "is_dno": {
+      "type": "boolean"
+    },
+    "number": {
+      "type": "string"
+    },
+    "number_type": {
+      "type": "string"
+    },
+    "operator": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "operator_note": {
+      "type": "string"
+    },
+    "score_avg": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "sightings_30d": {
+      "type": "integer"
+    },
+    "spam_label": {
+      "enum": [
+        "brak_danych",
+        "raczej_bezpieczny",
+        "podejrzany",
+        "niebezpieczny",
+        "dno_spoofing"
+      ],
+      "type": "string"
+    },
+    "total_opinions": {
+      "type": "integer"
+    },
+    "url": {
+      "type": "string"
+    },
+    "whitelist": {
+      "properties": {
+        "institution": {
+          "type": "string"
+        },
+        "label": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "verified_on": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "institution",
+        "verified_on"
+      ],
+      "type": [
+        "object",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "number",
+    "e164",
+    "spam_label",
+    "total_opinions",
+    "is_dno",
+    "url",
+    "attribution"
+  ],
+  "type": "object"
+}

First observedJun 11, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Adds substantial behavioral context beyond the annotations: the operator comes from UKE ranges with an MNP portability note, a risk label from opinions, DNO UKE registry status (with the spoofing caveat), a White List entry, and report counters. It also names the data source (numertel.pl), which is consistent with openWorldHint=false.

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 purpose, then use cases, then return values in a logical order. It is dense but each clause carries distinct information about what it returns, so little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Annotations cover the safety profile, an output schema exists, and the description still summarizes return fields. Nothing an agent needs to decide to call it or interpret it 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 coverage is 100% and the single 'number' parameter is fully described in the schema (9-digit format, +48 and spaces stripped). The description adds no parameter-level detail, so the baseline 3 applies.

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 ('Sprawdź reputację polskiego numeru telefonu') and immediately scopes it to Polish numbers, distinguishing it from siblings like check_scam_domain. An agent can tell exactly what this tool does without opening the schema.

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 explicit when-to-use triggers: who called, whether the number is spam/fraud, or whether a claimed bank/office phone is genuine. It does not name the alternative sibling find_official_number, so routing between the two is left partly to inference.

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

All numertel 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.