Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_avrdude

Destructive

Read, write, and verify AVR microcontrollers through an authorized programmer, using engagement-relative paths for firmware artifacts and workspace files.

Instructions

Read, write, and verify AVR microcontrollers through an authorized programmer. 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_avrdude"
  }
}

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, idempotentHint=false, so the agent knows this mutates external hardware. The description adds the engagement-namespace scoping and relative-path convention, which is useful context the schema does not carry. It does not, however, say what is destroyed (target flash/fuse memory), whether operations are recoverable, or how failures surface — the most important behavioral facts for an avrdude wrapper.

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?

Two short sentences, front-loaded with the core capability, with no filler. It could be slightly more informative without becoming verbose, but nothing present is wasted.

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. Still, for a destructive, open-world tool that forwards free-form CLI arguments with zero schema documentation, the description should at minimum describe the arguments format and the hardware-permission expectation. The namespace/path note is a good start but insufficient for the tool's complexity.

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 4 parameters, so the description must compensate and largely does not. Only the working-directory/path convention gets any explanation; the critical 'arguments' array — apparently raw avrdude CLI flags — and its format are never described, nor is 'stdin' clarified. That leaves an agent guessing at the primary input.

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 set of verbs (read, write, verify) against a specific resource (AVR microcontrollers via an authorized programmer), which lets an agent tell it apart from the other oc_* hardware/network tooling. It stops short of noting that it is a CLI passthrough wrapper, but the resource scope is 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?

Offers situational context — it operates on hardware through a programmer, runs in the selected engagement namespace, and expects relative paths for engagement artifacts. There is no explicit when-to-use versus an alternative, no prerequisite guidance (e.g., programmer must be attached/authorized), and no warnings about irreversible flash writes.

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