Skip to main content
Glama

Decompile Jeb Item

decompile_jeb_item
Idempotent

Decompile a single type or method into engine pseudo-code using Dalvik, Java, or native decompilers; read-only against the target file.

Instructions

Decompile one type or method to engine pseudo-code using its decompiler (Dalvik, Java, or native). item_address comes from the engine's code item listing; unit_path defaults to the engine's first code unit and stays unknown when omitted. Read-only with respect to the target file.

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": {
      "item_kind": "method",
      "item_address": "Lcom/example/Main;->onCreate()V"
    },
    "name": "decompile_jeb_item"
  }
}

Input Schema

NameRequiredDescriptionDefault
item_kindYesKind of item to decompile
unit_pathNoTarget code unit; the engine's first code unit in the project when omitted
item_addressYesType or method address within the unit, as listed by the engine

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare idempotentHint=true, destructiveHint=false, and openWorldHint=true; the description adds the notable qualifier that it is read-only with respect to the target file. That qualifier, however, sits in tension with readOnlyHint=false and the description never explains why the tool is flagged as non-read-only (e.g., project/session state changes), which is exactly the context an agent needs. Adding default-resolution behavior for unit_path is a useful extra.

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 short sentences, front-loaded with purpose, then parameter provenance, then the safety note — nothing obviously padded. The phrase 'stays unknown when omitted' is slightly ambiguous but does not bloat the text.

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?

For a single-item decompile tool with only two required parameters and no output schema, the description covers purpose, address provenance, unit fallback, and read-only scope adequately. The remaining gap — what the returned pseudo-code looks like and the meaning of the readOnlyHint=false flag — is modest but present.

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 schema already documents all three parameters, including the type/method enum and address format. The description restates the unit_path default and adds that it 'stays unknown when omitted' along with the provenance of item_address, but adds no format or syntax detail beyond what the schema provides. Baseline 3 applies.

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?

States a specific verb and resource — 'Decompile one type or method to engine pseudo-code' — and names the decompiler flavors (Dalvik, Java, native), which tells the agent what input shape to expect. The scope word 'one' implicitly separates it from batch-style siblings, but no sibling is named, so the agent must infer that batch_decompile or decompile_subgraph are the alternatives.

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?

It gives a real prerequisite — item_address must come from the engine's code item listing — which is genuine when-to-use context. However, it never says when to prefer this over batch_decompile or decompile_subgraph, nor what happens if the unit is not open, so usage selection is only implied.

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