Skip to main content
Glama
Sign In
usb-rea

usb-rea

by emirmrkaljevic
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

report

Generate a Markdown evidence document from a USB capture, linking each claim to frame numbers and summarizing device responses, handshake messages, and observations for human protocol review.

Instructions

Generate a Markdown evidence report: every claim links to frame numbers in the capture.

Includes a 'Device responses' section when the device answers queries (status polls, command ACKs, GET_REPORT), saying which reply bytes could not be explained, a 'Handshake' section for messages sent once before the first action (session setup, tokens), and an 'Observations' section for 'seen' markers (named readings and unmatched observations).

Read-only: returns Markdown text (does not write a file). Same inputs as diff_actions. Use after capture_stop (or on an existing pcap). Choose this over diff_actions when the human should read the protocol; choose scaffold_driver when they need a pyusb driver.

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": {
      "capture": "<capture>"
    },
    "name": "report"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoUSB device address to analyse; default = bus address with the most host→device payloads
labelsNoMarker-free mode: ';'-separated labels in click order, or a text file path (one label per line)
captureYesPath to a usbmon or USBPcap pcap/pcapng file
markersNoMarkers JSON path; default <capture>.actions.json. Ignored when labels is set

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.2.1
    • addedInput schema / properties / capture / description
      Added value: +"Path to a usbmon or USBPcap pcap/pcapng file"
    • addedInput schema / properties / device / description
      Added value: +"USB device address to analyse; default = bus address with the most host→device payloads"
    • addedInput schema / properties / labels
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Marker-free mode: ';'-separated labels in click order, or a text file path (one label per line)",
+  "title": "Labels"
+}
    • addedInput schema / properties / markers / description
      Added value: +"Markers JSON path; default <capture>.actions.json. Ignored when labels is set"
  2. First observedv0.2.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations are provided, so the description carries the burden and it does the most important part: 'Read-only: returns Markdown text (does not write a file)', pre-empting the natural assumption that a report tool persists output. It also notes the inputs match diff_actions, which bounds expectations, though it says nothing about cost or behavior on malformed pcaps.

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?

Front-loaded with the core action and output format, then the conditional sections, then routing guidance. Dense but every clause carries information; the parenthetical section list is slightly long but is the most useful part of the description.

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?

An output schema exists and the description still names the return medium (Markdown text, not a file) and the section structure, which is the right level of detail. With 4 params at full coverage and clear routing, an agent has what it needs; only error/failure behavior is unaddressed.

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%, including the non-obvious default-device heuristic and the labels/markers precedence, so the schema already does the heavy lifting. The description adds only 'Same inputs as diff_actions', which is a cross-reference rather than new parameter meaning. Baseline 3 applies.

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?

States a specific verb and artifact: 'Generate a Markdown evidence report' with 'every claim links to frame numbers in the capture'. The section breakdown (Device responses, Handshake, Observations) makes the output's shape concrete and distinguishes it from diff_actions and scaffold_driver by name.

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

Usage Guidelines5/5

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

Explicit lifecycle placement ('Use after capture_stop (or on an existing pcap)') plus a two-way routing rule: choose this over diff_actions 'when the human should read the protocol', choose scaffold_driver 'when they need a pyusb driver'. That is a full when/when-not/alternative mapping.

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