Skip to main content
Glama

Search Android Classes

search_android_classes
Idempotent

Search decompiler class-name rows in a local APK by case-sensitive substring; use an empty query to list all classes without executing the APK.

Instructions

Search complete decompiler class-name rows in an explicit local APK by case-sensitive substring. Empty query inventories all rows. Repeated names remain repeated and appear in duplicate_names; the provider accepts only class names for lookup, so these rows do not identify which same-name class node a later lookup selects. Retains artifact and engine identity; no APK execution.

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",
      "query": "Activity"
    },
    "name": "search_android_classes"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesLocal APK path; the target is never executed
queryYesCase-sensitive class-name substring; empty lists all classes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

The description adds genuine behavior beyond the annotations: duplicate names are not collapsed and surface in a duplicate_names field, results retain artifact and engine identity, and the target is never executed. The 'no APK execution' claim sits in mild tension with readOnlyHint=false, but since readOnlyHint commonly reflects session/engine state rather than file mutation, this is a conservative annotation rather than an outright contradiction.

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 tight sentences that front-load the action and then layer the duplicate-handling and safety caveats; no filler. It is somewhat dense with terminology ('decompiler class-name rows', 'engine identity'), but each clause carries distinct information.

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 partially compensates by disclosing the duplicate_names field and the retention of artifact/engine identity, plus the no-execution guarantee. What remains thin is the practical follow-up path for disambiguating same-name rows, which is mentioned only as a limitation rather than resolved.

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%, so both parameters (path, query) are already fully documented, including case sensitivity and empty-query semantics. The description restates those same facts without adding format, syntax, or performance guidance beyond the schema, so 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?

The description names a specific verb and resource ('Search complete decompiler class-name rows'), the exact target ('in an explicit local APK'), and the matching rule ('case-sensitive substring'). It also states the empty-query edge case, so the agent knows precisely what set of records this tool returns rather than guessing from the title.

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?

Usage context is implied rather than stated: 'Empty query inventories all rows' tells the agent how to get a full listing, and the remark that 'these rows do not identify which same-name class node a later lookup selects' hints that a lookup tool (e.g. inspect_android_class) is the follow-up step. However, no alternative is named and no when-not-to-use condition is given, leaving the agent to infer the handoff.

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