Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

set_data_table_row_fields

DestructiveIdempotent

Update only the specified cells in one DataTable row by deep-merging JSON fields onto the existing row, preserving untouched columns and sub-fields before saving.

Instructions

Write only the named cells of one DataTable row via the native JSON importer, deep-merged onto the current row so untouched columns and struct sub-fields survive, then save. Returns changed_columns, unchanged_despite_request, unknown_columns (skipped) and the row as ExportText. For many rows use set_data_table_rows_from_json.

Returns: { table_path, row_name, row_struct, success, saved, created, updated_existing, written_fields:[..], changed_columns:[..], unchanged_despite_request:[..], unknown_columns?:[..], problems:[..], row_after_exporttext:{column:exporttext} }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fieldsYesObject of {column_name: value} to overlay onto the current row (only these cells are written); a TMap<Enum,SoftClass> value must be an object of {EnumName: bare-class-path} (e.g. {"MyEnumValue":"/Game/...ABP_x_C"}) -- passed through verbatim, never wrapped
row_nameYesName (key) of the row to write
data_tableNoFull asset path of the DataTable (table_path also accepted)
table_pathNoAlias of data_table (the DataTable asset path, e.g. "/Game/Data/DT_Items"); data_table wins when both are given
create_if_missingNoWhen true, create the row (from defaults) if it does not exist; when false (default) a missing row is an error

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.0
    • addedInput schema / properties / table_path / description
      Added value: +"Alias of data_table (the DataTable asset path, e.g. \"/Game/Data/DT_Items\"); data_table wins when both are given"
    • changedInput schema / required
      Previous value: -[
-  "data_table",
-  "row_name",
-  "fields"
-]New value: +[
+  "row_name",
+  "fields"
+]
  2. First observedv1.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already carry destructiveHint=true, idempotentHint=true and readOnlyHint=false, yet the description adds real value: the deep-merge semantics that let untouched columns and struct sub-fields survive, that unknown columns are silently skipped, and that the row is saved. This clarifies the non-destructive-in-practice merge behavior that annotations alone would not convey.

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 first sentence carries purpose, mechanism and behavior; the alternative pointer follows. The prose already lists several return fields and the subsequent 'Returns:' block repeats them, introducing mild redundancy, though the structured block is still useful given no output schema exists.

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 mutating tool with no output schema, the description thoroughly enumerates the return payload (changed_columns, unchanged_despite_request, unknown_columns, problems, row_after_exporttext) and the deep-merge/creation behavior, so an agent has everything needed to call and interpret it.

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 description coverage is 100%, so the schema already documents fields, row_name, data_table/table_path and create_if_missing, including the TMap<Enum,SoftClass> value format. The description adds merge context but no field-level syntax or format detail beyond what the schema supplies, 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 (write only the named cells of one DataTable row) plus the mechanism (native JSON importer, deep-merged, then save). It routes the agent to the batch sibling set_data_table_rows_from_json, so it is distinguishable from a large DataTable family.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

Explicitly names the alternative for the many-rows case ('For many rows use set_data_table_rows_from_json'), which is clear usage guidance. However, it does not distinguish itself from the near-identical single-row siblings set_data_table_row / set_data_table_row_from_json, leaving some routing ambiguity.

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