Skip to main content
Glama

Catalog QA Desk

by app.openkrill
OverviewDiscussionsAdmin

Build a CSV of listing text fixes

listing_fix_sheet
Read-onlyIdempotent

Best for: "write the alt text for my images" or "fix the shouting titles". Builds a CSV of corrected titles and image alt text to review and import. Returns: csv with only the rows that change (URL handle, Title, Product image URL, Image position, Image alt text), 200 rows per call (pass next_offset for more), with counts per fix and a notice. It changes nothing in any store. Input tips: send exactly one of csv or domain. Optional fixes, any of alt_text, title_whitespace, title_caps (default all three), and alt_text_template with {title}, {vendor}, {type}, {position} (default "{title}"). Errors: both_given, missing_source, csv_too_large, or a feed refusal; then ask for the CSV. Not for: rewriting descriptions or changing a live store. Run listing_text_audit first to see what is wrong.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
csvNoThe 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"}
fixesNoWhich fixes to build, such as ["alt_text"]. alt_text: fill empty image alt text from the template. title_whitespace: trim and collapse spaces in titles. title_caps: rewrite all-capital titles in title case. Default: all three.
domainNoA 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"}
offsetNoRows to skip. Pass next_offset from the last answer, with the same source, fixes and template, for the next 200 rows.
alt_text_templateNoAlt text pattern, such as "{title} by {vendor}, view {position}". Placeholders: {title}, {vendor}, {type}, {position}; any other text is copied as written. Default "{title}".{title}

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
csvYesRows to import: URL handle, Title, Product image URL, Image position, Image alt text. Only rows that change are included.
hostNoThe store host that was read, in domain mode only
rowsYesData rows in csv, header not counted, at most 200 per call
noticeYesFixed reminder to pass on: the sheet is advisory and nothing was changed in any store
sourceYesWhere the products came from: the csv text or the store's public feed (domain)
totalsYesFixes found before the sheet was cut to 200 rows
productsYesProducts found in the source
truncatedYesTrue when more rows would change past this sheet
next_offsetNoPresent while rows remain: call again with this offset and the same inputs for the next rows
feed_truncatedNoPresent and true when the store has more products than the 5 pages read

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Rows to skip. Pass next_offset from the last answer, with the same source, fixes and template, for the next 200 rows.",
+  "minimum": 0,
+  "type": "integer"
+}
    • addedOutput schema / properties / next_offset
      Added value: +{
+  "description": "Present while rows remain: call again with this offset and the same inputs for the next rows",
+  "minimum": 1,
+  "type": "integer"
+}
    • changedOutput schema / properties / rows / description
      Previous value: -"Data rows in csv, header not counted"New value: +"Data rows in csv, header not counted, at most 200 per call"
    • changedOutput schema / properties / truncated / description
      Previous value: -"True when more than 200 rows would change"New value: +"True when more rows would change past this sheet"
  2. Changed3 schema fields changed
    • 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\"}"
  3. Changed24 schema fields changed
    • addedInput schema / properties / alt_text_template / default
      Added value: +"{title}"
    • changedInput schema / properties / alt_text_template / description
      Previous value: -"Alt text pattern with {title}, {vendor}, {type} and {position} placeholders (default \"{title}\")"New value: +"Alt text pattern, such as \"{title} by {vendor}, view {position}\". Placeholders: {title}, {vendor}, {type}, {position}; any other text is copied as written. Default \"{title}\"."
    • 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 / fixes / default
      Added value: +[
+  "alt_text",
+  "title_whitespace",
+  "title_caps"
+]
    • changedInput schema / properties / fixes / description
      Previous value: -"alt_text: fill empty image alt text from the template. title_whitespace: trim and collapse spaces in titles. title_caps: rewrite all-capital titles in title case. Default: all three."New value: +"Which fixes to build, such as [\"alt_text\"]. alt_text: fill empty image alt text from the template. title_whitespace: trim and collapse spaces in titles. title_caps: rewrite all-capital titles in title case. Default: all three."
    • 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 / notice / description
      Added value: +"Fixed reminder to pass on: the sheet is advisory and nothing was changed in any store"
    • addedOutput schema / properties / products / description
      Added value: +"Products found in the source"
    • addedOutput schema / properties / products / minimum
      Added value: +0
    • addedOutput schema / properties / rows / description
      Added value: +"Data rows in csv, header not counted"
    • addedOutput schema / properties / rows / maximum
      Added value: +200
    • addedOutput schema / properties / rows / 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 / totals / properties / alt_text / description
      Added value: +"Images given alt text"
    • addedOutput schema / properties / totals / properties / alt_text / minimum
      Added value: +0
    • addedOutput schema / properties / totals / properties / title_caps / description
      Added value: +"All-capital titles rewritten in title case"
    • addedOutput schema / properties / totals / properties / title_caps / minimum
      Added value: +0
    • addedOutput schema / properties / totals / properties / title_whitespace / description
      Added value: +"Titles with spaces trimmed"
    • addedOutput schema / properties / totals / properties / title_whitespace / minimum
      Added value: +0
    • addedOutput schema / properties / totals / required
      Added value: +[
+  "alt_text",
+  "title_whitespace",
+  "title_caps"
+]
    • addedOutput schema / properties / truncated / description
      Added value: +"True when more than 200 rows would change"
    • changedOutput schema / required
      Previous value: -[
-  "source",
-  "csv",
-  "rows",
-  "totals",
-  "truncated",
-  "notice"
-]New value: +[
+  "source",
+  "products",
+  "csv",
+  "rows",
+  "totals",
+  "truncated",
+  "notice"
+]
  4. Changed1 schema field changed
    • 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"
-}
  5. Changed1 schema field changed
    • 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"
+}
  6. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/destructive annotations, it discloses pagination behavior (200 rows per call, pass next_offset), the feed-refusal fallback ('large stores often block it; then ask the user for the CSV'), named error codes, and the reassurance that nothing changes in any store. This is unusually rich behavioral context that the annotations alone do not carry.

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 Best for / Returns / Input tips / Not for, and each block earns its place. It is dense and repeats a few schema facts (defaults, placeholders), so it is slightly longer than strictly necessary.

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?

Even though an output schema exists, the description still summarizes the return shape (URL handle, Title, Product image URL, Image position, Image alt text, counts, notice), covers both input paths, pagination, and failure modes. Nothing an agent needs to invoke this correctly is missing.

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 semantics not in the schema: that offset must be passed 'with the same source, fixes and template' as the prior call, and the exactly-one-of csv/domain rule. Defaults and placeholders are largely restated from the schema, keeping this below a 5.

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 artifact: 'Builds a CSV of corrected titles and image alt text to review and import.' It gives concrete user-intent examples ('write the alt text for my images', 'fix the shouting titles') and explicitly distinguishes itself from listing_text_audit, so an agent can route correctly 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Best for' / 'Not for' framing is explicit: not for rewriting descriptions or changing a live store, and 'Run listing_text_audit first to see what is wrong' names the prerequisite sibling. It also states exactly-one-of csv or domain, which is the key usage constraint.

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 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