Skip to main content
Glama

adb_firmware_diff

Compare firmware components across two OTA fingerprints or live device vs saved fingerprint to spot changes in baseband, bootloader, kernel, security patch, build ID, and Android version.

Instructions

Compare all firmware components between two saved OTA fingerprints, or between the current device state and a saved fingerprint. Compares baseband (with chipset-specific parsed component diffs), bootloader, kernel, security patch, build ID, and Android version.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "adb_firmware_diff"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoPath to 'to' fingerprint JSON (or 'current' to use live device state). Defaults to the most recent fingerprint.
fromNoPath to 'from' fingerprint JSON (or 'current' to use live device state). Defaults to the second-most-recent fingerprint.
deviceNoDevice serial (used when 'from' or 'to' is 'current', or for auto-selecting fingerprints)
result_handleNoOptional. If provided, store this tool's result under `result://<tool>/<name>` for retrieval after compaction. Name must be 1-32 chars, [a-zA-Z0-9_-]. Existing handles with the same tool+name are overwritten. Use adb_result_list to see active handles, adb_result_get or the MCP Resource URI to retrieve.
result_handle_ttlNoOptional. TTL in seconds for the result handle (60 to 604800). Default 43200 (12 hours). Ignored if result_handle is not provided.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.6
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed3 schema fields changedv1.1.3
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / result_handle
      Added value: +{
      +  "description": "Optional. If provided, store this tool's result under `result://<tool>/<name>` for retrieval after compaction. Name must be 1-32 chars, [a-zA-Z0-9_-]. Existing handles with the same tool+name are overwritten. Use adb_result_list to see active handles, adb_result_get or the MCP Resource URI to retrieve.",
      +  "maxLength": 32,
      +  "minLength": 1,
      +  "pattern": "^[a-zA-Z0-9_-]+$",
      +  "type": "string"
      +}
    • addedInput schema / properties / result_handle_ttl
      Added value: +{
      +  "description": "Optional. TTL in seconds for the result handle (60 to 604800). Default 43200 (12 hours). Ignored if result_handle is not provided.",
      +  "maximum": 604800,
      +  "minimum": 60,
      +  "type": "integer"
      +}
  3. First observedv1.1.1

TDQS

A4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the burden. The word "Compare" and the use of saved fingerprints imply a read-only analysis, and it discloses that baseband diffs are chipset-specific parsed diffs. However, it never states that no device modification occurs, what permissions/live-device requirements exist when 'current' is used, or what the diff output looks like when components match or are missing.

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?

Two sentences, zero filler, with the primary action and comparison modes front-loaded and the compared component list following. Nothing is redundant with the tool name or title.

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?

There is no output schema, and the enumerated components effectively tell the agent what the result covers. What is missing is how differences are presented (per-field old/new values, severity, absent-component handling), which would matter for an agent planning to parse the output, but the core capability is fully conveyed.

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%, so the defaults for 'from'/'to', the 'current' sentinel, the device serial semantics, and the result_handle/TTL contract are all already documented in the schema. The description adds no parameter-level meaning beyond that, which meets the baseline of 3 for fully covered schemas.

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 ("Compare") with a specific resource ("all firmware components") and enumerates the compared fields: baseband, bootloader, kernel, security patch, build ID, and Android version. It also distinguishes the two operating modes (fingerprint-vs-fingerprint, or live device vs fingerprint), which separates it from siblings like adb_firmware_probe and adb_firmware_history.

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

Usage Guidelines4/5

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

It clearly establishes the context in which the tool is used: comparing two saved OTA fingerprints or the current device state against a saved one. It does not explicitly name alternatives (e.g., prefer adb_firmware_probe to capture a fingerprint first) or state when not to use it, so it stops short of a full routing statement.

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