Skip to main content
Glama

White Automotive & Media Services Catalog

by com.whiteautoandmedia
OverviewDiscussionsAdmin

search_catalog

Search White Automotive & Media Services products by free text, for example "HMI module", "digital cluster Silverado" or "CarPlay retrofit". Returns a summary for each match: name, SKU, price, availability, categories, a short description and the product URL. Call get_product for full detail on a specific item. This endpoint does not determine fitment. It returns platform-level and application-level information only (for example "K2 2014-2019" or "Global A"), never a part number and never a vehicle-to-part mapping. Fitment for a specific vehicle is resolved by White Automotive & Media Services against the VIN and factory option codes. Do not assert that a product fits a particular vehicle. Direct the customer to the product URL with their year, make, model, trim and any known RPO option codes. Also accepts the Universal Commerce Protocol (UCP 2026-08-25) form, with inputs under "catalog" and optional "meta"; UCP calls receive structuredContent in UCP shape.

Input Schema

NameRequiredDescriptionDefault
metaNoUCP request metadata. meta["ucp-agent"].profile is the calling platform's profile URL (https).
limitNoMaximum results to return.
queryNoSearch terms. Maximum 120 characters.
catalogNoUCP search request. Needs query, filters.categories, or both.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / catalog
      Added value: +{
+  "description": "UCP search request. Needs query, filters.categories, or both.",
+  "properties": {
+    "filters": {
+      "properties": {
+        "categories": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "price": {
+          "description": "min and max in minor units (cents).",
+          "properties": {
+            "max": {
+              "minimum": 0,
+              "type": "integer"
+            },
+            "min": {
+              "minimum": 0,
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        }
+      },
+      "type": "object"
+    },
+    "pagination": {
+      "properties": {
+        "cursor": {
+          "type": "string"
+        },
+        "limit": {
+          "minimum": 1,
+          "type": "integer"
+        }
+      },
+      "type": "object"
+    },
+    "query": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
    • addedInput schema / properties / meta
      Added value: +{
+  "description": "UCP request metadata. meta[\"ucp-agent\"].profile is the calling platform's profile URL (https).",
+  "properties": {
+    "ucp-agent": {
+      "properties": {
+        "profile": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}
    • removedInput schema / required
      Removed value: -[
-  "query"
-]
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses the shape of returned summaries, the fitment limitation and the reason for it (VIN/option-code resolution), and that UCP-shaped calls return structuredContent rather than the default shape. It does not mention pagination behavior or result caps beyond the schema's limit maximum.

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, examples and return shape, then constraints. The fitment disclaimer spans three sentences and partially restates itself ('does not determine fitment' / 'never a vehicle-to-part mapping' / 'do not assert that a product fits'), which is a small amount of redundancy, though it does serve agent-safety guidance.

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?

For a search tool with no output schema and a nested dual-shape input, the description supplies return fields, the UCP form, and the critical fitment caveat. Pagination/cursor semantics are left entirely to the schema, a minor gap given the tool can return up to 20 results.

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; the description earns extra by explaining the dual invocation shape — the UCP variant takes inputs under "catalog" with optional "meta" — which the schema alone does not make obvious to an agent choosing between the two forms.

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 products) with three concrete example queries, and names what is returned per match (name, SKU, price, availability, categories, description, URL). It also explicitly differentiates from the sibling get_product, which handles full item detail.

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 explicit routing: use this for discovery, call get_product for full detail. It adds a strong negative constraint (this endpoint does not determine fitment) and a concrete alternative workflow (direct the customer to the product URL with year/make/model/trim/RPO codes).

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

All White Automotive & Media Services Catalog toolsInspect
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