Skip to main content
Glama
smk-h

embedded-mcp-toolkit

by smk-h

serial_open

Open a serial port connection to a device or TCP endpoint and start an interactive shell session, returning the initial banner output.

Instructions

Open a serial port connection and start an interactive shell session. Returns the initial banner output.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
portNoSerial port path (e.g. COM3, /dev/ttyUSB0) or TCP serial endpoint (tcp://host:port, e.g. QEMU with '-serial tcp:...'). Overrides device config if provided.
deviceNoDevice name (optional, defaults to the active device)
parityNoParity: none, even, or odd (default: none)
baudRateNoBaud rate (default: 115200)
dataBitsNoData bits: 5, 6, 7, or 8 (default: 8)
stopBitsNoStop bits: 1, 1.5, or 2 (default: 1)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.0.0
    • changedInput schema / properties / port / description
      Previous value: -"Serial port path (e.g. COM3, /dev/ttyUSB0). Overrides device config if provided."New value: +"Serial port path (e.g. COM3, /dev/ttyUSB0) or TCP serial endpoint (tcp://host:port, e.g. QEMU with '-serial tcp:...'). Overrides device config if provided."
  2. First observedv0.2.2

TDQS

B3.4/5.0
Behavior2/5

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It states that a connection is opened and the initial banner is returned, but it does not disclose session persistence, exclusivity, authentication/login requirements, or failure behavior. For a stateful operation this is a significant gap.

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?

The description is a single front-loaded sentence that states the primary operation, the interactive-session behavior, and the return type. There is no filller or redundant restatement of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given six parameters, no annotations, and no output schema, the description is too thin. It does not explain how this tool relates to serial_shell_login or serial_close, whether login is needed before using the shell, or what happens if the port is already in use. The banner-output note is helpful but incomplete contextual guidance.

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?

The input schema already documents all 6 parameters with 100 percent coverage, including defaults and the port-override behavior. The description adds no parameter-specific detail beyond the general notion of a serial port connection, so the baseline score of 3 is appropriate.

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 uses a specific verb and resource: it opens a serial port connection and starts an interactive shell session. It also names a distinctive behavior, returning the initial banner output, and is clearly distinguishable from the sibling ssh_* and adb_* open tools as well as serial_exec.

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 phrase 'interactive shell session' implies this is for interactive use rather than one-off commands, but the description does not explicitly compare to serial_exec, serial_shell_login, or other serial tools. An agent must infer when to use this instead of a sibling.

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