Skip to main content
Glama

split_column_into_table

Move what a column repeats into a table of its own: ONE record of a new table per different value of the column (a supplier, a client, a category named on many rows), made from the values the table already holds — never invented — and a link field added to the table, filled for every row. Use it for «split X into their own table», «make suppliers a separate table», «normalise». The old columns stay as they are; the answer says what to tell the person about them. Do NOT use create_form for this: it makes an empty table. It is also the FIRST step of a list that depends on another field when that field is a plain dropdown (Stage → Check point): split the dropdown — its options become the parents' table — then link the children's column to it with into_table.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "app_id": "<app_id>",
      "entity_id": "<entity_id>",
      "column": "<column>"
    },
    "name": "split_column_into_table"
  }
}

Input Schema

NameRequiredDescriptionDefault
app_idYesProject ID (from list_projects)
columnYesThe field (name or id) whose values name the things — «Supplier»
entity_idYesThe table that holds the column now
into_tableNoA table the project ALREADY has (name or id) whose rows the column names: no table is made, the column is linked to that table's rows with the same values — e.g. the stage dropdown of «Check points» linked to «Stages», so a list on another form can depend on it
table_nameNoThe new table's name, in the person's language — «Suppliers»
with_columnsNoOther fields of the same table that describe the same thing and go with it — «Supplier email», «Supplier phone»

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / into_table
      Added value: +{
      +  "description": "A table the project ALREADY has (name or id) whose rows the column names: no table is made, the column is linked to that table's rows with the same values — e.g. the stage dropdown of «Check points» linked to «Stages», so a list on another form can depend on it",
      +  "type": "string"
      +}
  2. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare not-destructive, non-idempotent, closed-world, and non-read-only. The description adds real behavioral context beyond that: values are 'never invented' (existing values only), a link field is added and 'filled for every row', and the old columns remain unchanged. It does not state reversibility or failure modes, so not a 5.

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 almost every clause carries information (mode, exclusion, dependent-list workflow). It is a dense run-on with layered parentheticals, which costs a little readability, but there is no filler.

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?

No output schema exists, so the description carries the return burden; it addresses this with 'the old columns stay... the answer says what to tell the person about them', though that return description is vague. For a mutation tool with only non-destructive annotations, the operation, its two modes, and its side effects are otherwise well covered.

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 schema already documents all six parameters (baseline 3). The description goes further by explaining the into_table mode (no new table is made; the column is linked to an existing table's matching rows) and the role of with_columns ('other fields that describe the same thing'), adding meaning beyond the schema text.

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 precise verb+resource and outcome: move a repeated column's distinct values into a new table, one record per value, with a link field back to the source. It explicitly distinguishes itself from the sibling create_form and describes the into_table variant, so an agent can tell it apart from create_table/create_form 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?

Gives explicit trigger phrases («split X into their own table», «make suppliers a separate table», «normalise»), an explicit exclusion ('Do NOT use create_form for this: it makes an empty table'), and a conditional workflow ('FIRST step of a list that depends on another field... then link the children's column with into_table'). When/how-not/alternatives are all present.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources