Skip to main content
Glama

Create an owned tmux session

new_session

Creates a detached tmux session owned by tmux-mcp with optional working directory, shell, and initial command; returns an existing owned session unchanged and never modifies foreign sessions.

Instructions

Create a detached session owned by tmux-mcp, with an optional working directory, shell, and initial command. If an owned session with that name exists it is returned unchanged; a foreign session with that name is never modified.

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": {
      "name": "<name>"
    },
    "name": "new_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoAbsolute working directory (default: host home)
nameYesSession name (letters, digits, dash, underscore)
shellNoAbsolute shell path (default: /usr/bin/bash)
commandNoOptional command to type after creation

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does a solid job: it discloses that sessions are detached, that they are owned by tmux-mcp, that creation is idempotent for owned names, and that foreign sessions are never touched — important safety context. It stops short of describing error behavior or what a failed initial command does.

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

Conciseness5/5

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

Two sentences, front-loaded with the creation action, then the collision/idempotency rule. No filler and nothing that repeats structured fields verbatim.

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 creation tool with no output schema, the definition covers the action, the ownership model, and the existing-name behavior — enough to call it correctly. The main remaining gap is return-value shape and failure modes, which the description only hints at ('returned unchanged').

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 cwd, shell, name, and command are already fully documented in the schema. The description only restates them at a high level ('optional working directory, shell, and initial command') and adds no format or constraint detail beyond the schema, so baseline 3 applies.

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 ('Create a detached session') plus the scope qualifier 'owned by tmux-mcp', which distinguishes it from generic tmux operations and from the read/kill siblings. It does not explicitly name an alternative, but the ownership framing makes the purpose unambiguous.

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

Usage Guidelines3/5

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

The description implies usage through the idempotency rule ('if an owned session with that name exists it is returned unchanged') and the ownership boundary ('a foreign session with that name is never modified'), which helps an agent decide what will happen. However, it gives no explicit when-to-use vs. alternatives guidance, such as pairing with exec or send_keys.

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