Skip to main content
Glama

John's Essentials

by com.johnsessentials
OverviewDiscussionsAdmin

convert_parquet

Parquet Converter — Convert Apache Parquet to CSV, TSV, JSON, NDJSON or Excel — and back. Types are preserved in both directions: numbers stay numbers in JSON, blank cells become real nulls in Parquet, and identifier columns like '01924' stay text instead of losing their leading zero. Flat schemas only; nested or repeated columns are reported rather than silently flattened. [category: convert]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toYes'jsonl' is accepted as an alias for ndjson. One side of the pair must be parquet — table→table pairs belong to convert_data.
fileYesA .parquet file, or a .csv/.tsv/.json/.ndjson/.xlsx table to turn into Parquet.
fromNoOptional but recommended when uploading csv/tsv/json/ndjson: those are indistinguishable by content, so declare which one it is.
sheetNoWhich worksheet to read. Leave it blank for the first one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / from / x-ui
      Added value: +{
+  "unset_label": "Read from file"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / sheet / description
      Previous value: -"Optional: when the source is .xlsx, which worksheet to read (default: the first)."New value: +"Which worksheet to read. Leave it blank for the first one."
    • addedInput schema / properties / sheet / x-show-when
      Added value: +{
+  "from": [
+    "xlsx"
+  ]
+}
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

The description goes well beyond annotations by explaining type preservation: numbers stay numeric, blank cells become actual nulls, and identifier strings keep leading zeros. It also discloses a limitation up front, flat schemas only, and states that nested/repeated columns are reported rather than silently flattened rather than claiming unsupported behavior.

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?

The core conversion behavior is front-loaded in the first sentence, and the additional behavioral caveats are compact and purposeful. Minor redundancy exists in the leading 'Parquet Converter' phrase and the trailing '[category: convert]' tag, which add little beyond the tool name and sibling context.

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 four-parameter file conversion tool with no output schema, the description covers the main operation, supported formats, type-preservation semantics, and schema limitations. It lacks an explicit statement about the output artifact or return shape, but the parameter and schema details cover most invocation needs.

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 every parameter, which establishes a baseline of 3. The description adds meaningful context about type fidelity, but it does not explain specific parameter behavior, formats, or aliases beyond what the schema provides.

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?

The description states a specific verb and resource: convert Apache Parquet to CSV, TSV, JSON, NDJSON, or Excel, and back. It also adds a differentiating constraint by implying Parquet must always be one side of the conversion, which separates this from generic table-to-table converters like convert_data.

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?

The description plus schema guidance makes the intended usage clear: Parquet is always one side of the pair. The to-parameter schema explicitly routes table-to-table conversions away to convert_data, and the from-parameter guidance explains when declaring the source format is recommended.

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

All John's Essentials toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources