SheetShift

Split column

split_column

Read-onlyIdempotent

Split one column into several columns on a delimiter (e.g. 'full name' on a space), inserted in place; short rows are padded with empty cells. Returns the table in the same format. Use when one column packs several values. Do NOT use to clean or change format; use clean_table or convert_table.

Input Schema

TableJSON Schema

Name	Required	Description
`data`	Yes	The whole table as text, first row = header. CSV/TSV text (quoted cells allowed), or a JSON array of flat objects, e.g. "name,age\nAsha,30".
`column`	Yes	Column to use: the exact header name (case-sensitive), or a 0-based column index as digits, e.g. "price" or "2".
`format`	No	Format of 'data' and of the returned table: csv, tsv or json. Default csv.
`delimiter`	Yes	Literal text to split on, e.g. " ", "-" or "\|".
`new_names`	No	Header names for the new columns; count must equal the maximum number of parts. Default <column>_1, <column>_2, ...

Output Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes	The resulting table as text in the input format.
`parts`	Yes	Number of new columns the split produced.

Schema Changelog

Changes observed during successful MCP inspections.

Changed16 schema fields changedOct 10, 2026

changedInput schema / properties / column / description

Previous value: -"The column for this request."New value: +"Column to use: the exact header name (case-sensitive), or a 0-based column index as digits, e.g. \"price\" or \"2\"."

addedInput schema / properties / column / minLength
```
Added value: +1
```

changedInput schema / properties / data / description

Previous value: -"The data for this request."New value: +"The whole table as text, first row = header. CSV/TSV text (quoted cells allowed), or a JSON array of flat objects, e.g. \"name,age\\nAsha,30\"."

addedInput schema / properties / data / minLength
```
Added value: +1
```

changedInput schema / properties / delimiter / description

Previous value: -"The delimiter for this request."New value: +"Literal text to split on, e.g. \" \", \"-\" or \"|\"."

addedInput schema / properties / delimiter / minLength
```
Added value: +1
```

changedInput schema / properties / format / description

Previous value: -"The format for this request."New value: +"Format of 'data' and of the returned table: csv, tsv or json. Default csv."

addedInput schema / properties / format / enum

Added value: +[
+  "csv",
+  "tsv",
+  "json"
+]

changedInput schema / properties / new_names / description

Previous value: -"List of new names values."New value: +"Header names for the new columns; count must equal the maximum number of parts. Default <column>_1, <column>_2, ..."

removedOutput schema / properties / data

Removed value: -{
-  "description": "The modified data string with the column split into new columns.",
-  "type": "string"
-}

removedOutput schema / properties / errors

Removed value: -{
-  "description": "An array of error messages, if any, encountered during the split operation.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

removedOutput schema / properties / new_columns

Removed value: -{
-  "description": "An array of new column names created from the split operation.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

addedOutput schema / properties / parts

Added value: +{
+  "description": "Number of new columns the split produced.",
+  "type": "integer"
+}

removedOutput schema / properties / status

Removed value: -{
-  "description": "The status of the operation, indicating whether it was successful or if there were any errors.",
-  "type": "string"
-}

addedOutput schema / properties / text

Added value: +{
+  "description": "The resulting table as text in the input format.",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "data",
-  "new_columns",
-  "status"
-]New value: +[
+  "text",
+  "parts"
+]

Changed5 schema fields changedOct 6, 2026
- addedInput schema / properties / column / description
```
Added value: +"The column for this request."
```
- addedInput schema / properties / data / description
```
Added value: +"The data for this request."
```
- addedInput schema / properties / delimiter / description
```
Added value: +"The delimiter for this request."
```
- addedInput schema / properties / format / description
```
Added value: +"The format for this request."
```
- addedInput schema / properties / new_names / description
```
Added value: +"List of new names values."
```

Changed1 schema field changedOct 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "data": {
+      "description": "The modified data string with the column split into new columns.",
+      "type": "string"
+    },
+    "errors": {
+      "description": "An array of error messages, if any, encountered during the split operation.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "new_columns": {
+      "description": "An array of new column names created from the split operation.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "status": {
+      "description": "The status of the operation, indicating whether it was successful or if there were any errors.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "data",
+    "new_columns",
+    "status"
+  ],
+  "type": "object"
+}

First observedOct 2, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description still adds non-obvious behavior: rows are split in place and short rows are padded with empty cells, which tells the agent what the output shape will be for ragged data.

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?

Front-loads the operation and its in-place/padding semantics, then the usage condition, then the exclusion, in four tight sentences with no filler.

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?

With an output schema present and full annotation and schema coverage, the description only needs to frame purpose and routing, which it does; the padding note and 'returns the table in the same format' remove any residual ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all five parameters, including the format enum and new_names default, are documented in the schema. The description restates the delimiter concept with examples but adds no format or naming guidance beyond it, so the baseline 3 applies.

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 ('Split one column into several columns on a delimiter') with a concrete example ('full name' on a space). It names sibling tools it is not, so an agent can distinguish it from clean_table and convert_table without opening 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 when-to-use ('Use when one column packs several values') plus an explicit exclusion with named alternatives ('Do NOT use to clean or change format; use clean_table or convert_table'). Both the positive and negative routing conditions are covered.

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

All SheetShift 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.