Skip to main content
Glama

table_transform

Reshape tabular data by transposing, selecting columns, renaming, sorting, deduping, or filtering rows. Convert between Markdown, CSV, TSV, JSON, and HTML.

Instructions

Reshape a table: transpose, pick or rename columns, sort, dedupe, filter.

Prefer this over editing rows by hand when the change is mechanical, because the whole table is processed at once and row order is preserved.

Args: text: The whole table as text. operation: What to do. transpose | select_columns | rename_columns | sort | dedupe | drop_empty_rows | filter. from_format: How to read the input. markdown, csv, tsv, json or html. to_format: How to write the result. markdown, csv, tsv, json or html. columns: For select_columns: the column names to keep, in output order. A 1-based column number is also accepted, e.g. "2". renames: For rename_columns: a mapping of old name to new name. sort_by: For sort: the column to sort on. descending: For sort: set true for descending order. numeric: For sort: set true to sort numerically instead of as text. column: For filter: the column to test. operator: For filter: == | != | > | >= | < | <= | contains | startswith | endswith | empty | not_empty. value: For filter: the value to compare against. aligns: Markdown output only. Per-column alignment or a single value.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
valueNo
alignsNo
columnNo
columnsNo
numericNo
renamesNo
sort_byNo
operatorNo
operationYes
to_formatNomarkdown
descendingNo
from_formatNomarkdown

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It usefully states that the whole table is processed at once and row order is preserved, but does not mention statelessness, error handling, or data-size limits. Coverage is partial but not misleading.

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?

The description is front-loaded with a one-line summary, followed by a usage guideline and a structured Args block. Given 13 parameters and no schema descriptions, the detail in the Args block is necessary. Every sentence earns its place; there is no redundancy.

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?

For a complex tool with 13 parameters and an output schema, the description covers all parameters and operation options, and the output schema handles return-structure explanation. Some edge cases (e.g., empty input, invalid format behavior) are unspecified, but an agent can correctly call the tool with the given information.

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

Parameters5/5

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

Schema description coverage is 0%, and the description's Args section fully compensates: it explains every parameter, including operation-specific behavior (e.g., 1-based column numbers for select_columns, the operator list for filter, and format options). This goes well beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('reshape') and resource ('a table'), and enumerates the supported operations (transpose, select_columns, rename_columns, sort, dedupe, filter). This makes the core purpose clear. It does not explicitly name sibling tools, so differentiation from tools like table_convert or table_align is implicit rather than spelled out.

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?

The description provides a clear usage context: prefer this over manual row editing for mechanical changes, citing whole-table processing and row-order preservation. It does not, however, mention when to use sibling tools such as table_convert or table_align, leaving alternative selection to inference.

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