Skip to main content
Glama

Inspect Android Class

inspect_android_class
Idempotent

Inspect one exact Android class's parsed methods, fields, and inner classes, including synthetic members, to get display signatures and unknown DEX descriptors without generating source code.

Instructions

Inspect one exact Android class's parsed methods, fields and inner classes, including synthetic members. Returns display signatures and explicit unknown DEX descriptors without generating source. Overload indices remain consistent within the artifact and engine session.

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",
      "class_name": "example.MainActivity"
    },
    "name": "inspect_android_class"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesLocal APK path; the target is never executed
class_nameYesExact fully qualified class name

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations, the description discloses meaningful behavior: synthetic members are included, unknown DEX descriptors are surfaced explicitly, no source is generated, and overload indices are stable within the artifact and engine session. It does not explain why readOnlyHint is false for an inspection tool (presumably artifact loading/session state), which is the one gap an agent might stumble on.

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 front-loaded sentences: what is inspected, what is returned, and a session-scoped caveat. The final sentence about overload indices is jargon-heavy but carries real information; nothing is redundant.

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 the work of indicating return shape (display signatures, unknown-descriptor markers). For a two-parameter, non-destructive inspection tool this is nearly complete; only error behavior for a missing/nonexistent class name 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 coverage is 100% and both parameters are documented in-schema, including 'the target is never executed' and 'Exact fully qualified class name'. The description reinforces the exactness requirement ('one exact Android class') but adds no format, casing, or path-syntax detail beyond the schema.

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 ('Inspect one exact Android class') and enumerates the payload (parsed methods, fields, inner classes, synthetic members), which clearly separates it from a search or package-level tool. It never names a sibling such as inspect_android_method or search_android_classes, so the differentiation is inferred rather than explicit.

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?

The word 'exact' implies this is an exact-name lookup rather than a search, which implies you should have already resolved the class name elsewhere. However, there is no explicit when-to-use/when-not statement, no prerequisite that the APK must be loaded first, and no routing to inspect_android_method or inspect_android_package alternatives.

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