Skip to main content
Glama
ellmos-codecommander-mcp

ellmos-codecommander-mcp

Fix Encoding

cc_fix_encoding
Idempotent

Repairs encoding errors such as Mojibake and double UTF-8 in files, with optional dry-run preview and backup creation.

Instructions

Repairs encoding errors (Mojibake, double UTF-8).

Args:

  • path (string): Path to the file

  • dry_run (boolean): Preview only

  • create_backup (boolean): Create backup

Repairs 27+ Mojibake patterns (German, French, Spanish).

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": {
      "path": "<path>"
    },
    "name": "cc_fix_encoding"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesPath to the file
dry_runNoPreview only
create_backupNoCreate backup

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.3.27
    • removedInput schema / additionalProperties
      Removed value: -false
  2. First observedv1.3.8

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the safety profile is largely covered. The description adds that a backup is created by default and that a preview mode exists, which is useful mutation context, but it says nothing about in-place overwrite behavior, what happens when no pattern matches, or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly half the text is a hand-copied Args block duplicating schema descriptions that are already 100% covered. The most differentiating content, the 27+ Mojibake pattern scope, is buried in the final sentence rather than front-loaded.

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 mutating, idempotent file-repair tool with no output schema, the description should say whether changes are written in place, what the backup file is named, and how this differs from cc_fix_umlauts. Those gaps remain, though the annotations plus the pattern-scope sentence give an agent enough to call it safely.

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%, and the 'Args' block restates the schema descriptions verbatim without adding syntax, constraints, or examples. Baseline 3 applies since the schema already carries full parameter documentation and the description adds nothing new here.

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?

States a specific verb and resource ('Repairs encoding errors') and names the concrete defect classes (Mojibake, double UTF-8) plus 27+ patterns across German/French/Spanish. It does not, however, distinguish itself from the sibling cc_fix_umlauts, which on its name alone appears to overlap heavily with this tool's scope.

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

Usage Guidelines2/5

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

No statement of when to reach for this tool versus cc_fix_umlauts, cc_convert_format, or cc_scan_emoji, and no prerequisites (e.g., file must be text, should run dry_run first). The only usage-adjacent hint is the parameter name 'dry_run', which is not framed as guidance.

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