Catalog QA Desk

Audit product listing text

listing_text_audit

Read-onlyIdempotent

Best for: "which products have no alt text?", "are any descriptions copied?" or "which descriptions are too thin?". Returns: four lists, up to 100 entries each: no_alt (images without alt text), duplicate_descriptions, thin_descriptions and title_issues, with totals before the cut. Input tips: send exactly one of csv (a Shopify product CSV) or domain (a store address such as example.com); optional min_words, the word count below which a description is thin (default 20). Domain mode reads the public product feed once, after robots.txt. Errors: both_given, missing_source, csv_too_large, or a feed refusal; then ask for the CSV. Not for: writing the fixes (use listing_fix_sheet), GTINs or Merchant Center rules (use merchant_feed_check).

Input Schema

TableJSON Schema

Name	Required	Description
`csv`	No	The full text of a Shopify product CSV, header row first, such as "Title,URL handle,Description,Vendor,Price,...". Paste the file exported from Shopify admin (Products > Export) as it is. At most 2 MB; split a larger file by rows and repeat the header in each part. Example call: {"csv": "Title,URL handle,Price\nWool Beanie,wool-beanie,24.00"}
`domain`	No	A store address such as example.com, sent instead of csv (send exactly one of the two). The store's public /products.json is read once (at most 5 pages of 250 products), after its robots.txt. Large stores often block it; then ask the user for the CSV. Example call: {"domain": "example.com"}
`min_words`	No	A description with fewer words than this counts as thin, such as 30. Default 20.

Output Schema

TableJSON Schema

Name	Required	Description
`host`	No	The store host that was read, in domain mode only
`no_alt`	Yes	Images with empty alt text, at most 100
`source`	Yes	Where the products came from: the csv text or the store's public feed (domain)
`totals`	Yes	Counts before each list was cut to 100
`products`	Yes	Products found in the source
`truncated`	Yes	True when any list had more than 100 entries
`title_issues`	Yes	One entry per product and title problem, at most 100
`feed_truncated`	No	Present and true when the store has more products than the 5 pages read
`thin_descriptions`	Yes	Products whose description has fewer words than min_words, at most 100
`duplicate_descriptions`	Yes	Descriptions of 5 or more words shared by several products, at most 100 groups

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 13, 2026

addedInput schema / anyOf

Added value: +[
+  {
+    "required": [
+      "csv"
+    ]
+  },
+  {
+    "required": [
+      "domain"
+    ]
+  }
+]

changedInput schema / properties / csv / description

Previous value: -"The full text of a Shopify product CSV, header row first, such as \"Title,URL handle,Description,Vendor,Price,...\". Paste the file exported from Shopify admin (Products > Export) as it is. At most 2 MB; split a larger file by rows and repeat the header in each part."New value: +"The full text of a Shopify product CSV, header row first, such as \"Title,URL handle,Description,Vendor,Price,...\". Paste the file exported from Shopify admin (Products > Export) as it is. At most 2 MB; split a larger file by rows and repeat the header in each part. Example call: {\"csv\": \"Title,URL handle,Price\\nWool Beanie,wool-beanie,24.00\"}"

changedInput schema / properties / domain / description

Previous value: -"A store address such as example.com, sent instead of csv (send exactly one of the two). The store's public /products.json is read once (at most 5 pages of 250 products), after its robots.txt. Large stores often block it; then ask the user for the CSV."New value: +"A store address such as example.com, sent instead of csv (send exactly one of the two). The store's public /products.json is read once (at most 5 pages of 250 products), after its robots.txt. Large stores often block it; then ask the user for the CSV. Example call: {\"domain\": \"example.com\"}"

Changed42 schema fields changedOct 11, 2026

changedInput schema / properties / csv / description

Previous value: -"The product CSV text exactly as exported from Shopify, header row included. At most 2 MB."New value: +"The full text of a Shopify product CSV, header row first, such as \"Title,URL handle,Description,Vendor,Price,...\". Paste the file exported from Shopify admin (Products > Export) as it is. At most 2 MB; split a larger file by rows and repeat the header in each part."

changedInput schema / properties / domain / description

Previous value: -"A store address such as example.com, instead of csv. The store's public /products.json is read once (at most 5 pages of 250 products), after its robots.txt. Large stores often block it."New value: +"A store address such as example.com, sent instead of csv (send exactly one of the two). The store's public /products.json is read once (at most 5 pages of 250 products), after its robots.txt. Large stores often block it; then ask the user for the CSV."

addedInput schema / properties / min_words / default
```
Added value: +20
```

changedInput schema / properties / min_words / description

Previous value: -"A description with fewer words than this counts as thin (default 20)"New value: +"A description with fewer words than this counts as thin, such as 30. Default 20."

addedOutput schema / properties / duplicate_descriptions / description

Added value: +"Descriptions of 5 or more words shared by several products, at most 100 groups"

addedOutput schema / properties / duplicate_descriptions / items / properties / excerpt / description
```
Added value: +"The first 80 characters of the shared description"
```
addedOutput schema / properties / duplicate_descriptions / items / properties / handles / description
```
Added value: +"URL handles of the products that share it"
```
addedOutput schema / properties / duplicate_descriptions / items / properties / handles / minItems
```
Added value: +2
```
addedOutput schema / properties / duplicate_descriptions / items / required
```
Added value: +[
+  "excerpt",
+  "handles"
+]
```

changedOutput schema / properties / feed_truncated / description

Previous value: -"True when the store has more products than the five pages read"New value: +"Present and true when the store has more products than the 5 pages read"

changedOutput schema / properties / host / description

Previous value: -"The store read, in domain mode"New value: +"The store host that was read, in domain mode only"

addedOutput schema / properties / no_alt / description

Added value: +"Images with empty alt text, at most 100"

addedOutput schema / properties / no_alt / items / properties / handle / description

Added value: +"The product's URL handle (the item id for a Google Merchant feed file)"

addedOutput schema / properties / no_alt / items / properties / image / description
```
Added value: +"The image URL"
```

addedOutput schema / properties / no_alt / items / properties / position / description

Added value: +"The image's position in the product gallery, from 1; null when the source gives none"

addedOutput schema / properties / no_alt / items / properties / row / description

Added value: +"Spreadsheet row of the image, header is row 1; 0 in domain mode"

addedOutput schema / properties / no_alt / items / properties / row / minimum
```
Added value: +0
```

addedOutput schema / properties / no_alt / items / required

Added value: +[
+  "handle",
+  "image",
+  "position",
+  "row"
+]

addedOutput schema / properties / products / description
```
Added value: +"Products found in the source"
```
addedOutput schema / properties / products / minimum
```
Added value: +0
```

addedOutput schema / properties / source / description

Added value: +"Where the products came from: the csv text or the store's public feed (domain)"

addedOutput schema / properties / thin_descriptions / description

Added value: +"Products whose description has fewer words than min_words, at most 100"

addedOutput schema / properties / thin_descriptions / items / properties / handle / description
```
Added value: +"The product's URL handle (the item id for a Google Merchant feed file)"
```
addedOutput schema / properties / thin_descriptions / items / properties / words / description
```
Added value: +"Words in the description; 0 when it is empty"
```
addedOutput schema / properties / thin_descriptions / items / properties / words / minimum
```
Added value: +0
```
addedOutput schema / properties / thin_descriptions / items / required
```
Added value: +[
+  "handle",
+  "words"
+]
```

addedOutput schema / properties / title_issues / description

Added value: +"One entry per product and title problem, at most 100"

addedOutput schema / properties / title_issues / items / properties / handle / description
```
Added value: +"The product's URL handle (the item id for a Google Merchant feed file)"
```

addedOutput schema / properties / title_issues / items / properties / problem / description

Added value: +"One of: empty title, extra whitespace, longer than 150 characters, all capitals, promotional text, very short (under 10 characters)"

addedOutput schema / properties / title_issues / items / properties / title / description
```
Added value: +"The title, cut to 80 characters"
```
addedOutput schema / properties / title_issues / items / required
```
Added value: +[
+  "handle",
+  "title",
+  "problem"
+]
```
addedOutput schema / properties / totals / properties / duplicate_descriptions / description
```
Added value: +"All groups of shared descriptions"
```
addedOutput schema / properties / totals / properties / duplicate_descriptions / minimum
```
Added value: +0
```
addedOutput schema / properties / totals / properties / no_alt / description
```
Added value: +"All images without alt text"
```
addedOutput schema / properties / totals / properties / no_alt / minimum
```
Added value: +0
```
addedOutput schema / properties / totals / properties / thin_descriptions / description
```
Added value: +"All thin descriptions"
```
addedOutput schema / properties / totals / properties / thin_descriptions / minimum
```
Added value: +0
```
addedOutput schema / properties / totals / properties / title_issues / description
```
Added value: +"All title problems"
```
addedOutput schema / properties / totals / properties / title_issues / minimum
```
Added value: +0
```

addedOutput schema / properties / totals / required

Added value: +[
+  "no_alt",
+  "duplicate_descriptions",
+  "thin_descriptions",
+  "title_issues"
+]

addedOutput schema / properties / truncated / description

Added value: +"True when any list had more than 100 entries"

changedOutput schema / required

Previous value: -[
-  "source",
-  "no_alt",
-  "duplicate_descriptions",
-  "thin_descriptions",
-  "title_issues",
-  "totals",
-  "truncated"
-]New value: +[
+  "source",
+  "products",
+  "no_alt",
+  "duplicate_descriptions",
+  "thin_descriptions",
+  "title_issues",
+  "totals",
+  "truncated"
+]

Changed1 schema field changedOct 5, 2026

removedOutput schema / properties / note_from_openkrill

Removed value: -{
-  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
-  "type": "string"
-}

Changed1 schema field changedOct 4, 2026

addedOutput schema / properties / note_from_openkrill

Added value: +{
+  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
+  "type": "string"
+}

First observedOct 3, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds behavior beyond that: domain mode reads the public /products.json once after robots.txt, capped at 5 pages of 250 products, and large stores often block it so the CSV should be requested instead; CSV input is capped at 2 MB with a splitting instruction. These are operational constraints an agent cannot get from the annotations or 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?

Four labeled blocks (Best for / Returns / Input tips / Not for) put routing decisions first and mechanics second, with no filler sentences. Every clause carries a decision-relevant fact: trigger questions, return shape, input constraint, or error fallback.

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?

Output schema exists, yet the description still notes the four returned lists and the pre-cut totals, which is useful framing rather than redundancy. Combined with the source-selection rule, feed limits, error codes and sibling routing, an agent has everything needed to choose and invoke this tool correctly.

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 and the schema already defines both source parameters and min_words. The description adds marginal but real value: it restates the exactly-one-of constraint between csv and domain and clarifies min_words semantics (threshold below which a description counts as thin, default 20). It does not add format or syntax detail beyond the schema, so it stays just above baseline.

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?

The description names a specific verb (audit) and resource (product listing text) and immediately grounds it in concrete user questions ('which products have no alt text?', 'are any descriptions copied?'). The 'Not for' clause names the sibling tools that cover adjacent work (listing_fix_sheet, merchant_feed_check), so the agent can separate this tool from them without reading any schema.

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?

It gives explicit trigger questions ('Best for: ...'), explicit exclusions with the alternative tool for each ('Not for: writing the fixes (use listing_fix_sheet), GTINs or Merchant Center rules (use merchant_feed_check)'), and the input rule that exactly one of csv or domain must be sent. Error branches (both_given, missing_source, csv_too_large, feed refusal) each come with a stated next action.

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

All Catalog QA Desk 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.