OnlyMCP

Write a skill file

skill_file_write

DestructiveIdempotent

Create or replace one companion file of a skill: a script, template or reference that sits next to its SKILL.md. Meant for files beside the skill body; the SKILL.md itself is written with the skill. Text goes in as utf8, a binary file as base64. Replacing overwrites the whole file. A file may hold 2 MB, a skill 300 files and 24 MB in all. Answers "Saved / ( bytes)". Docs: https://only-mcp.com/docs/import-and-sync#keep-clients-in-step

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": {
      "skill": "<skill>",
      "path": "<path>",
      "content": "<content>"
    },
    "name": "skill_file_write"
  }
}

Input Schema

Name	Required	Description
`path`	Yes	Path inside the skill, for example scripts/scan.sh.
`skill`	Yes	The skill name.
`content`	Yes	The full new content.
`encoding`	No	utf8 for text, base64 for binary. Defaults to utf8.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare destructive=true, idempotent=true and readOnly=false; the description adds genuinely new behavior: replacing overwrites the whole file, per-file and per-skill limits (2 MB / 300 files / 24 MB), encoding rules, and the exact response string. That is meaningful context beyond the annotation set, though it doesn't cover failure modes such as what happens when a limit is exceeded.

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?

Front-loads the core verb and scope, then packs constraints into short clauses with no filler. The trailing docs link is mildly promotional but does not obscure the operational content.

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?

No output schema exists, and the description supplies the return string, the overwrite semantics, the size and count limits, and the encoding split. That covers everything an agent needs to invoke a write tool of this complexity 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 coverage is 100%, so all four parameters are already documented in the schema. The description only reinforces the encoding choice (utf8 vs base64) and implies content is a full replacement rather than a patch; it adds no new syntax, path, or naming rules beyond the schema example.

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 specific verb and resource: 'Create or replace one companion file of a skill: a script, template or reference that sits next to its SKILL.md.' It also explicitly distinguishes the resource from SKILL.md itself, so an agent can separate it from skill_write without opening either 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?

Gives clear context ('Meant for files beside the skill body') and an explicit exclusion ('the SKILL.md itself is written with the skill'), which routes the agent elsewhere. It does not name the sibling tool directly, so the alternative is implied rather than spelled out.

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

All OnlyMCP tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?