catalog

Search parts

search_parts

Read-only

Search the Satmarin catalog by part number, model or free text. Order: exact SKU (case and separators ignored), SKU prefix, then words found in the title or description in any order. A word that names an antenna model, such as v100NX, also matches parts fitted to that model. Use the model filter to restrict results to one model or series.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_parts"
  }
}

Input Schema

Name	Required	Description
`brand`	No	Exact brand slug, e.g. intellian.
`limit`	No	Default 10, maximum 25.
`model`	No	Antenna model or series, name or slug, e.g. v100NX or v-Series. Case and spacing are ignored; an unrecognised model returns an error.
`query`	Yes	Part number, model or free text.
`part_type`	No	Part type slug.

Output Schema

Name	Required	Description	Default
`match`	Yes
`total`	Yes
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 1, 2026

changedOutput schema / properties / results / items / properties / price / description

Previous value: -"EUR, ex works, VAT excluded. null when the part is discontinued or has no list price."New value: +"The price in the currency this product is priced in, ex works, VAT excluded. No conversion is applied and there is no single catalogue currency: read `currency` on every row. null when the part is discontinued, is priced on request, or has no list price."

changedOutput schema / properties / results / items / properties / price / properties / currency / enum
```
Previous value: -[
-  "EUR"
-]New value: +[
+  "EUR",
+  "USD"
+]
```

addedOutput schema / properties / results / items / properties / price_on_request

Added value: +{
+  "description": "true when the catalogue quotes this product rather than listing a price, so `price` is null but the product is quotable. Discontinued products are not this.",
+  "type": "boolean"
+}

changedOutput schema / properties / results / items / required

Previous value: -[
-  "sku",
-  "product_id",
-  "title",
-  "brand",
-  "part_type",
-  "compatible_models",
-  "price",
-  "eol",
-  "superseded_by",
-  "url"
-]New value: +[
+  "sku",
+  "product_id",
+  "title",
+  "brand",
+  "part_type",
+  "compatible_models",
+  "price",
+  "price_on_request",
+  "eol",
+  "superseded_by",
+  "url"
+]

Changed3 schema fields changedSep 14, 2026

changedInput schema / properties / brand / description

Previous value: -"Exact brand slug."New value: +"Exact brand slug, e.g. intellian."

changedInput schema / properties / model / description

Previous value: -"Antenna model slug."New value: +"Antenna model or series, name or slug, e.g. v100NX or v-Series. Case and spacing are ignored; an unrecognised model returns an error."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "match": {
+      "enum": [
+        "exact_sku",
+        "prefix",
+        "text"
+      ],
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "properties": {
+          "brand": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "compatible_models": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "eol": {
+            "type": "boolean"
+          },
+          "part_type": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "price": {
+            "description": "EUR, ex works, VAT excluded. null when the part is discontinued or has no list price.",
+            "properties": {
+              "amount": {
+                "type": "number"
+              },
+              "basis": {
+                "enum": [
+                  "EXW"
+                ],
+                "type": "string"
+              },
+              "currency": {
+                "enum": [
+                  "EUR"
+                ],
+                "type": "string"
+              }
+            },
+            "required": [
+              "amount",
+              "currency",
+              "basis"
+            ],
+            "type": [
+              "object",
+              "null"
+            ]
+          },
+          "product_id": {
+            "type": "integer"
+          },
+          "sku": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "superseded_by": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "title": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "sku",
+          "product_id",
+          "title",
+          "brand",
+          "part_type",
+          "compatible_models",
+          "price",
+          "eol",
+          "superseded_by",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "minimum": 0,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "results",
+    "total",
+    "match"
+  ],
+  "type": "object"
+}

First observedSep 12, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds genuinely non-obvious behavior — the exact-SKU → SKU-prefix → title/description word ranking, and that a model-named word such as v100NX also matches parts fitted to that model. It does not mention the unrecognized-model error path, but that is documented in the schema.

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 tight sentences, front-loaded with what is searched, then match ordering, then the filter recommendation. No filler or redundant restatement of the schema.

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, full schema coverage, and read-only annotations, the description covers what an agent needs to call it correctly. Gaps are minor — nothing about empty-result behavior or result truncation beyond the schema's limit field.

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 description coverage is 100%, so the baseline is 3; the description goes beyond the schema by explaining how the query string is interpreted and ranked, and by clarifying the purpose of the model filter as a scope restriction. It doesn't add semantics for brand or part_type, keeping it at 4.

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 ('Search the Satmarin catalog') plus the three query modes (part number, model, free text), which no sibling (check_compatibility, get_quote, resolve_supersession) covers. An agent can immediately distinguish this as the catalog-lookup tool.

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 operating context — the ranking order used and explicit advice to 'Use the model filter to restrict results to one model or series.' It stops short of naming when not to use it or pointing to a sibling alternative, so it is strong but not exhaustive.

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

All catalog 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?