Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_screen

Destructive

Executes screen commands in an isolated engagement namespace with explicit argv tokens and optional stdin, enabling terminal session management without shell parsing.

Instructions

Run screen from the OpenCyber embedded toolkit. The container executes screen directly with the supplied argv tokens; shell parsing is never used. Runs from the selected engagement namespace; use relative paths for engagement artifacts.

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": {
      "engagement_id": "<engagement_id>",
      "arguments": "<arguments>"
    },
    "name": "oc_screen"
  }
}

Input Schema

NameRequiredDescriptionDefault
stdinNo
argumentsYes
engagement_idYes
working_directoryNo.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, openWorldHint=true, idempotentHint=false, so the risk profile is declared. The description adds genuinely useful behavior beyond that: argv is passed as discrete tokens with no shell parsing, and the process runs inside the engagement namespace, which shapes path handling. It does not mention interactive/TTY requirements or what state `screen` may leave behind.

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?

Three short sentences with the core action front-loaded and no filler. The execution-model detail (no shell parsing) follows immediately, and the namespace/path note is last, which is a sensible ordering.

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?

An output schema exists, so return values need not be explained. However, for a destructive, open-world exec tool with four undocumented parameters, the description leaves the `stdin` channel and any interactivity expectations unaddressed, which an agent needs to call this 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 description coverage is 0%, so the description has to carry the parameter meaning. It partially does: 'supplied argv tokens' maps to `arguments`, and 'runs from the selected engagement namespace / use relative paths' maps to `engagement_id` and `working_directory`. The `stdin` parameter is never mentioned, which is a notable omission for an interactive terminal tool.

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: it runs the `screen` binary from the OpenCyber embedded toolkit, and clarifies that the container executes it directly with argv tokens rather than through a shell. That distinguishes it from shell-executing siblings like oc_bash, though it never says what `screen` itself is (terminal multiplexer) for an agent unfamiliar with the binary.

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?

Usage context is implied rather than stated: it says execution happens from the selected engagement namespace and that relative paths should be used for engagement artifacts. There is no explicit when-to-use versus oc_bash or other exec siblings, and no note about what kind of task warrants `screen` over a plain command run.

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