Skip to main content
Glama

create_composite_data_table

Create or re-converge a UCompositeDataTable by merging parent DataTables, letting a fork extend upstream rows instead of replacing them; validates parent row structs to prevent editor hangs.

Instructions

Create (or re-converge) a UCompositeDataTable whose row map is the merge of its parent DataTables, so a fork can EXTEND an upstream table instead of replacing it. The parent list is SET, not appended (re-running with a different list rewrites it), the row struct of every parent is validated BEFORE assignment (a mismatch or a cyclic parent chain would make the engine open a modal dialog and hang the editor), and the merge is verified by re-reading the live row map.

Returns: { table_name, package_path, table_path, table_class, row_struct, created, already_existed, requested_parent_tables, missing_parents, parents_applied, saved, save_error, parent_tables, parent_count, contributing_parent_count, merged_row_count, sum_parent_row_counts, expected_merged_row_count, merged_row_count_matches_parents, parent_row_struct_mismatch, shadowed_rows, shadowed_row_count, row_sources_included, row_sources? }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
row_structNoOptional UScriptStruct name for the composite rows. Defaults to the row struct of the first resolved parent (or, on an existing composite, to the one it already has -- which cannot be changed in place).
table_nameYesName of the composite DataTable asset to create or converge.
package_pathNoTarget content package path where the asset lives (check the body for the default).
parent_tablesYesArray of full asset paths of the parent DataTables, LOW precedence first: a row present in several parents is won by the one with the HIGHEST index.
include_row_sourcesNoOptional bool (default false): also return the winning parent for EVERY merged row. Expensive on large tables.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare the safety profile (not read-only, not destructive). The description goes well beyond that: a row-struct mismatch or cyclic parent chain triggers an engine modal dialog that hangs the editor, parents are validated before assignment, the parent list is SET rather than appended, and the merge is verified by re-reading the live row map. This is exactly the pre-invocation hazard context an agent needs.

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?

Purpose is front-loaded in the first clause, and every subsequent sentence carries non-redundant risk information. The dense run-on sentence packs multiple constraints together, and the exhaustive Returns list is long but earns its place since there is no output schema.

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 no output schema, the description fully enumerates the return fields (created, parents_applied, merged_row_count, mismatch flags, shadowed_rows, etc.) plus the editor-hang hazard. Combined with annotations covering the safety profile, an agent has everything needed to call and interpret this correctly.

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 all five parameters including precedence ('HIGHEST index wins') and default behavior. The description reinforces the 'SET not appended' semantics of parent_tables but adds little parameter-level detail beyond what the schema provides; baseline 3 is appropriate.

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 (create/converge a UCompositeDataTable) and immediately characterizes its distinguishing behavior: merging parent row maps so a fork EXTENDS an upstream table rather than replacing it. This separates it cleanly from sibling create_data_table and fork_class_chain 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 Guidelines4/5

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

Clearly frames the use case (fork extending upstream) and warns that re-running with a different parent list rewrites it, which tells the agent when re-invocation is safe. It implies the replacement-based alternative but does not name a specific sibling tool to route to, so it stops short of explicit when-not guidance.

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