Skip to main content
Glama
Sign In
Sora Commander

Sora Commander

by kurojack-jp
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

create_file

Creates one new UTF-8 text file in configured roots only after the local Owner GUI reviews its path and full content; existing targets, links, and protected names are rejected.

Instructions

DEV_ONLY: ask the local Owner GUI to create one new text file in configured roots, showing its path and complete content first. Existing targets are never overwritten; links and protected names are rejected; no command or job spawn. UNKNOWN requires manual reconciliation, never retry or assumed rollback.

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>",
      "content": "<content>"
    },
    "name": "create_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute absent file under configured Owner roots; existing parent directory required, never overwrite.
contentYesFull proposed UTF-8 text, at most 65536 bytes; may contain secrets. Avoid submitting secrets; the complete content is shown to the local Owner GUI before creation.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full behavioral burden and does so well: it discloses the Owner GUI approval step and that the full path and content are shown first, that existing targets are never overwritten, that links and protected names are rejected, that nothing is spawned, and the UNKNOWN/no-retry/no-rollback failure protocol. That is unusually rich disclosure of side effects, safety checks, and recovery expectations for a mutation tool.

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?

It is front-loaded with the DEV_ONLY gate and core action, then packs constraints into short semicolon-separated clauses with little waste. The final clause about UNKNOWN is compressed to the point of being cryptic, which costs a bit of clarity.

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?

An output schema exists, so return-value detail is correctly omitted, and the mutation/safety semantics are well covered despite the absence of annotations. The one gap is the undefined 'UNKNOWN' outcome term, which an agent cannot map to a concrete status without outside knowledge.

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 schema already documents 'path', 'content', the 65536-byte bound, secrecy exposure, and the Owner GUI display. The description restates the same preview-before-create behavior rather than adding new meaning, so the baseline 3 applies.

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 ('create one new text file in configured roots') plus a deployment gate ('DEV_ONLY'), which distinguishes it from siblings like create_directory, preview_source_create, and move_file. An agent can tell immediately that this is single-file creation, not a general write or patch tool.

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?

It gives clear preconditions and exclusions: DEV_ONLY, configured roots only, single new file, no overwrite, no command or job spawn, and manual reconciliation on UNKNOWN. It stops short of naming an alternative tool (e.g. preview_source_create or create_directory) for adjacent cases, so routing between siblings still requires inference.

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

Deploy Server

Other Tools