Skip to main content
Glama

Project Android Application Graph

project_android_application_graph
Idempotent

Projects authenticated APK evidence into an execution-free Android app inventory. Reports component paths, hashes, runtime-family hints, and bridge hypotheses without DEX decoding or APK execution.

Instructions

Project authenticated APK inventory_artifact Evidence into an execution-free Android application inventory. Reports exact component paths and hashes, runtime-family hints, and path-based bridge hypotheses without decoding DEX, executing the APK, or claiming observed runtime calls.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "inventory_evidence": "<inventory_evidence>"
    },
    "name": "project_android_application_graph"
  }
}

Input Schema

NameRequiredDescriptionDefault
inventory_evidenceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, and the description adds real value by defining the epistemic boundary (no DEX decoding, no execution, no claims of observed runtime calls), which is consistent with idempotency. However, for a non-read-only projection it never says where the inventory is written, what happens to prior projections, or what 'authenticated' evidence entails, leaving the mutation side undisclosed.

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?

A single front-loaded sentence that leads with the action and then constrains it; every clause (outputs, no-decode, no-execute, no runtime claims) carries weight. It is dense jargon but not padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

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 a fair job of naming what the projection yields and what it refuses to claim. Against a deeply nested 1-parameter input and a non-read-only annotation, though, it omits input expectations and persistence behavior, so a caller still needs the schema and trial calls.

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 0% and the single required parameter (inventory_evidence) is only hinted at as 'authenticated APK inventory_artifact Evidence'. The description does not explain that it is a list of fully-formed evidence records with required fields like evidence_id, subject, confidence and authority, so the agent must open the nested schema to construct a valid call.

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 ('Project ... into an execution-free Android application inventory') plus the resource, and enumerates the outputs (component paths and hashes, runtime-family hints, path-based bridge hypotheses). The Android scope implicitly separates it from the apple/harmony/managed projection siblings, but it never names an alternative explicitly.

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 is only implied through negative scope: 'without decoding DEX, executing the APK, or claiming observed runtime calls' tells the agent when this is inappropriate but not which sibling to pick instead. It also gives no preconditions such as requiring pre-recorded inventory_artifact Evidence to exist.

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