Skip to main content
Glama
ebcdicjp-mcp

ebcdicjp-mcp

by yukijames25

write_records

Build a fixed-length EBCDIC test file from JSON records and a COBOL copybook; missing fields become spaces or zeros, and non-round-trip characters are reported.

Instructions

Build a fixed-length EBCDIC file (test data) from JSON records shaped like read_records output. Missing fields are spaces / zero. Reports characters that will not read back the same (〜 → ~).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "records": "<records>",
      "copybook": "<copybook>",
      "output_path": "<output_path>",
      "codepage": "<codepage>"
    },
    "name": "write_records"
  }
}

Input Schema

NameRequiredDescriptionDefault
rdwNo
recordNo
recordsYes
codepageYesCode page of the system that will read the file: ibm930 (katakana) or ibm939 (lowercase).
copybookYesAbsolute path to the COBOL copybook
output_pathYes
copybook_encodingNoauto = UTF-8, else Shift_JIS (cp932)auto

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries real behavioral weight: it discloses default fill behavior for missing fields (spaces/zero) and that the tool detects and reports characters that will not round-trip (〜 → ~). It omits whether an existing output_path is overwritten, how errors surface, and what the 'report' looks like.

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?

Two short sentences, front-loaded with the core action, with the round-trip caveat placed last where it is useful. The parenthetical (〜 → ~) is terse to the point of being slightly cryptic without context, but nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter write tool with no annotations and no output schema, the description covers the essential quirk (lossy character round-trip, default fill) but leaves the write side underspecified: overwrite behavior, RDW option meaning, path constraints, and the format of the reported warnings are all absent.

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

Parameters2/5

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

Schema description coverage is 43%, below the threshold where the schema can shoulder the load, so the description should compensate. It clarifies that records must be JSON objects shaped like read_records output, but says nothing about output_path, copybook, copybook_encoding, rdw, or the singular record parameter.

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?

"Build a fixed-length EBCDIC file (test data) from JSON records" gives a concrete verb, resource, and output format, and it names the inverse operation (read_records) as the input shape reference. An agent can tell what this does and how it differs from read_records without inspecting the 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?

The description establishes the context (generate test data) and the input precondition (records shaped like read_records output), which effectively steers the agent toward this tool for file generation rather than encode_text for individual fields. It does not explicitly state when not to use it or name an alternative, so it stops short of full routing guidance.

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