Decompile APK or DEX files to Java, audit permissions and v1/v2/v3 signature schemes, and detect CWE vulnerabilities and hardcoded secrets.
5-Pass native Dalvik DEX decompiler. Audits permissions, keystore signature schemes (v1/v2/v3), CWE vulnerabilities, hardcoded secrets, and lifts Dalvik bytecode to Java classes.
| Name | Required | Description | Default |
|---|---|---|---|
| max_classes | No | Max classes to decompile | |
| target_path | Yes | Absolute path to APK or DEX |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses the five-pass analysis and audit categories, but omits whether the target is modified, permission requirements, artifact/file output, and response shape; it is minimum viable but incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact sentences front-load the core decompiler identity and then list capabilities. The audit list earns its space by signaling scope, and there is no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex decompiler/audit tool with no annotations or output schema, the definition explains what is analyzed but not what is returned or whether artifacts are written. Parameter coverage is complete, but the missing output and side-effect context leaves a clear gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters are fully documented in the schema, so the baseline is 3. The description adds no details about target_path or max_classes beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific operation and resource ('Dalvik DEX decompiler') and enumerates the audits plus Java lifting. It is clear what the tool does, though it does not explicitly contrast with sibling decompilers such as decompile_ios_ipa_package or decompile_entire_program.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No sentence states when to choose this over sibling decompilers or when not to use it. The Dalvik/DEX scope implies a use case, but the guidance is entirely inferential and there are no explicit alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.