Skip to main content
Glama

Inspect Android Package

inspect_android_package
Idempotent

Inspect a local APK's package, SDK and permission declarations, decoded manifest and class/resource counts without executing it. Use summary detail for declarations and counts alone, or complete to read the retained manifest.

Instructions

Inspect a local APK's package, SDK and permission declarations, decoded manifest and class/resource counts. Omitted or complete detail preserves the complete result. Select detail: "summary" for all declarations, engine identity and counts without decoded manifest text or duplicate raw calls; retains the complete source and returns a distinct linked inspect_analysis_view summary. Read the exact retained manifest with view kind android, facet manifest, offset and limit (UTF-16 code units), using normalized_result.parent_evidence_id. Does not execute the APK or verify signatures. Requires a caller-supplied JADX MCP JAR and JDK; uses one worker in an isolated temporary workspace.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "/tmp/Example.apk"
    },
    "name": "inspect_android_package"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesLocal APK path; the target is never executed
detailNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: the APK is never executed and signatures are not verified, a caller-supplied JADX MCP JAR and JDK are required, and processing uses one worker in an isolated temporary workspace. Those are exactly the prerequisites and side-effect profile an agent needs for a readOnlyHint=false, openWorldHint=true tool, and they are consistent with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and constraints are front-loaded, but the middle section is a run-on tangle ('Omitted or complete detail preserves the complete result', 'retains the complete source and returns a distinct linked inspect_analysis_view summary') and the trailing manifest-reading sentence describes a different tool. Tightening would make the detail semantics far easier to parse.

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?

With no output schema, the description does supply what a result contains: declarations, engine identity, counts, and a linked analysis view for the summary variant. Together with the prerequisites and non-execution caveats, it covers a moderately complex tool well; only the exact shape of the complete result is left implicit.

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

Parameters4/5

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

The schema covers 'path' but leaves 'detail' as a bare enum, and the description fills that gap by defining what 'summary' drops and returns versus the complete default. The offset/limit (UTF-16 code units) and 'view kind android, facet manifest' details belong to inspect_analysis_view rather than this tool's parameters, which risks an agent misplacing them, but they are framed as follow-up instructions.

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 resource: inspecting a local APK for package, SDK and permission declarations, decoded manifest, and class/resource counts. It also scopes the tool to local files (implicitly distinguishing it from device-oriented siblings like inspect_adb_package) and names inspect_analysis_view as the follow-up surface for the manifest text.

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?

Explicitly tells the agent how to choose 'detail': the default/complete path preserves the full result, while 'summary' omits decoded manifest text and duplicate raw calls and yields a linked inspect_analysis_view. It also directs how to read the retained manifest afterwards. It does not explain when to prefer this over other inspection entry points, but the local-APK scope does most of that work.

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