Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_openocd

Destructive

Drive JTAG/SWD targets through OpenOCD using interface and target configs, a passed-in debug probe, and engagement-relative paths for debugging and firmware work.

Instructions

Drive JTAG/SWD targets through OpenOCD using an interface and target config. Requires the debug probe to be passed into the container. 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_openocd"
  }
}

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

B3.2/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, non-idempotent and non-read-only, so the safety profile is carried structurally. The description usefully adds the hardware and container-mount prerequisite and the namespace/relative-path behavior. It omits the most consequential trait — that the call forwards a raw argument list to OpenOCD, so what is destroyed depends entirely on those arguments.

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, front-loaded with the capability, then prerequisites, then path scoping — no filler. Slight redundancy between the namespace sentence and the working_directory parameter, but nothing that wastes a line.

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 no explanation, and the hardware/path context is covered. The critical gap is that an agent is never told the argument list is passed verbatim to OpenOCD, which for a destructive, open-world tool is the one thing it most needs before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across four parameters, so the description must carry the load and largely does not. It hints that interface and target config are supplied but never explains that `arguments` is a raw argv passthrough, nor what `stdin` or `working_directory` do beyond the path remark.

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?

The description states a specific verb and resource — driving JTAG/SWD targets via OpenOCD — and adds the config inputs (interface, target config) that shape the call. It does not differentiate itself from any sibling, though none of the listed names obviously overlap, so the purpose stands on its own without explicit routing.

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?

It gives real prerequisites (the debug probe must be passed into the container) and path conventions (run from the engagement namespace, use relative paths for artifacts), which is more than implied usage. However, it never says when to reach for this tool versus other flashing/debug paths, nor any exclusions such as target-busy or exclusive-access conditions.

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