vivid-ads-commerce

Search catalogue

vivid_search

Read-onlyIdempotent

Search the Vivid Ads catalogue by product name, category, or intended use (e.g. 'corflute', 'pull up banner', 'expo', 'shopfront'). Returns matching products grounded in Vivid's own Shopify collections, so it also surfaces same-range, same-purpose alternatives — products flagged sameRange:true come from the top match's curated collection (returned as collection). ALWAYS mention these to the customer (e.g. 'we have two Pull Up Banner options, and Fabric Banner Stands do the same job'). Treat a from-price as INDICATIVE only — use vivid_product for options then vivid_price for the exact configuration. Paginated: returns total, has_more and next_offset; pass offset to get the next page.

Input Schema

Name	Required	Description
`limit`	No	max products to return (default 8)
`query`	Yes	what the customer is looking for (a product name, a category, or a use-case like 'expo' or 'shopfront')
`offset`	No	skip this many results — use next_offset from the previous page (default 0)

Output Schema

Name	Required	Description
`count`	No
`query`	No
`total`	No
`offset`	No
`status`	Yes	outcome discriminator, e.g. ok / priced / need_size / manual_quote / unknown_product / error
`message`	No
`has_more`	No
`products`	No
`agent_note`	No
`collection`	No
`next_offset`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 20, 2026

addedInput schema / properties / limit

Added value: +{
+  "description": "max products to return (default 8)",
+  "maximum": 25,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / offset

Added value: +{
+  "description": "skip this many results — use next_offset from the previous page (default 0)",
+  "minimum": 0,
+  "type": "integer"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "agent_note": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "collection": {},
+    "count": {
+      "type": "integer"
+    },
+    "has_more": {
+      "type": "boolean"
+    },
+    "message": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "next_offset": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "offset": {
+      "type": "integer"
+    },
+    "products": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "from": {
+            "description": "indicative from-price, AUD incl. GST — NOT a configured price"
+          },
+          "name": {
+            "description": "product title"
+          },
+          "product": {
+            "description": "product handle — pass to vivid_product / vivid_price"
+          },
+          "reason": {
+            "description": "why it matched"
+          },
+          "sameRange": {
+            "description": "true = same-range alternative from the top match's collection"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "query": {},
+    "status": {
+      "description": "outcome discriminator, e.g. ok / priced / need_size / manual_quote / unknown_product / error",
+      "type": "string"
+    },
+    "total": {
+      "type": "integer"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "type": "object"
+}

First observedJul 19, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the readOnly/idempotent/openWorld annotations by disclosing that results are grounded in Shopify collections, that `sameRange:true` products come from the top match's curated collection, and that a from-price is indicative only. It also documents pagination signals (total, has_more, next_offset).

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 core action and then layered with the highest-value caveats (sameRange, indicative pricing, pagination). It is dense and long, but nearly every clause carries operational weight; only the parenthetical customer-quote example is slightly expendable.

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?

An output schema exists, so return-shape explanation is not needed, yet the description still flags the key fields to act on (sameRange, collection, total, has_more, next_offset). Combined with sibling routing and the pricing caveat, it is complete for a search tool.

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 real meaning: the query field's use-case framing is exemplified, and offset is tied to next_offset from the previous page rather than being a bare integer. Limit's max behaviour is left to the schema.

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 Vivid Ads catalogue') and narrows scope to product name, category, or intended use with concrete examples. It also names overlapping siblings (vivid_product, vivid_price) so an agent can distinguish this tool without reading their schemas.

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?

Explicit routing rules: use vivid_product for options and vivid_price for exact configuration after a from-price. It also states a mandatory interaction policy ('ALWAYS mention these to the customer') and explains when to pass offset. Both when-to-use and how-to-continue are covered.

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

All vivid-ads-commerce 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?