Skip to main content
Glama

add_chooser_column_to_table

Append a new column to a UChooserTable asset in one undo step, compile and save it. Handles Randomize columns specially, ensuring at most one exists.

Instructions

Append a column of column_type, its input left unbound, to a UChooserTable asset as one undo step, then compile and save the table; success is false, with save_error, when the save fails. Each call appends a new column, even of a type the table already has, except Randomize: a table holds at most one, so an existing Randomize column is returned with already_existed=true and nothing changes. The new column gets one cell, its DefaultRowValue, per row already in the table, so columns and rows stay in step whichever is added first. Besides the types listed under column_type it accepts OutputFloat, OutputBool, OutputName, OutputEnum, ObjectClass, Name, MultiEnum and Randomize.

Returns: { table_path: string, column_index: int, column_name: string, column_type: string, already_existed: bool, row_count?: int, saved?: bool, save_error?: string }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
table_pathYesLong package path of an existing UChooserTable.
column_nameYesLabel echoed back in the reply only; it is not stored on the column.
column_typeYesColumn struct to append: "FloatRange", "Bool", "Enum", "Object", or "OutputObject".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.2
    • changedInput schema / properties / column_name / description
      Previous value: -"Label echoed back in the reply only: it is not stored on the column and plays no part in duplicate detection, which goes by column_type."New value: +"Label echoed back in the reply only; it is not stored on the column."
  2. Changed1 schema field changedv1.2.0
    • changedInput schema / properties / column_name / description
      Previous value: -"Display name; used to detect duplicates (already_existed = true if a column of this type is matched)."New value: +"Label echoed back in the reply only: it is not stored on the column and plays no part in duplicate detection, which goes by column_type."
  3. First observedv1.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly=false, idempotent=false, destructive=false) by disclosing the undo-step boundary, the automatic compile-and-save, the failure contract (saved=false + save_error), and the Randomize dedup rule returning already_existed=true with no mutation. The per-row DefaultRowValue cell creation explains the table's internal consistency guarantees.

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-loads the core action and keeps the edge cases (Randomize, row/cell syncing) tight, with the Returns object standing in for the absent output schema. Slightly dense and the 'columns and rows stay in step' clause is a touch redundant, but nothing is wasted.

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?

For a 3-param mutation tool with no output schema, the definition covers the mutation scope, failure mode, dedup exception, row/cell synchronization, and includes an inline Returns contract. Nothing an agent needs to call it 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 genuinely adds meaning by listing eight additional accepted column_type values (OutputFloat, OutputBool, OutputName, OutputEnum, ObjectClass, Name, MultiEnum, Randomize) beyond the five enumerated in the schema. That expansion is critical for correct invocation; table_path and column_name are already fully covered by 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 precise verb+resource ('Append a column ... to a UChooserTable asset') and immediately scopes it as one undo step plus compile/save. An agent can distinguish it from remove_chooser_column, add_chooser_row, and set_chooser_column_default without opening 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 Guidelines3/5

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

Usage is implied through the append semantics and the interaction with rows ('whichever is added first'), but it never names an alternative tool or states an explicit when-to-use/when-not condition relative to siblings like create_chooser_table or add_chooser_row. Adequate but leaves routing to inference.

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

Deploy Server

Other Tools