Skip to main content
Glama
starshield-forensics

starshield-forensics

by Ziqi

Precheck Chromium / Electron Local LevelDB Storage

starshield_precheck_leveldb
Read-onlyIdempotent

Run a read-only millisecond GO/PARTIAL/NO_GO feasibility check on local Chromium/Electron IndexedDB/LevelDB folders or .log/.ldb files without exposing raw content.

Instructions

Perform a read-only millisecond diagnostic and GO/PARTIAL/NO_GO feasibility check on a local Chromium browser or Electron desktop app (VS Code, Slack, Microsoft Teams, Discord, WhatsApp Desktop) IndexedDB/LevelDB directory or .log/.ldb file without leaking raw content.

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": {
      "target_path": "<target_path>"
    },
    "name": "starshield_precheck_leveldb"
  }
}

Input Schema

NameRequiredDescriptionDefault
schema_modeNoJSON record schema filter (default: auto).auto
target_pathYesLocal path to a Chromium/Electron IndexedDB/LevelDB folder or .log/.ldb file.

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?

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description still adds real value beyond them: a sub-millisecond cost expectation, a tri-state GO/PARTIAL/NO_GO verdict vocabulary, and an explicit guarantee that raw content is not leaked. It does not explain what distinguishes PARTIAL from NO_GO, which keeps it at 4.

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?

It is a single front-loaded sentence that names the action, the artifact, the verdict output, and the privacy property in one pass, with no filler or repetition. It is dense to the point of being a slight run-on, but every clause carries 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 usefully supplies the return vocabulary (GO/PARTIAL/NO_GO) and the privacy contract, which is what an agent most needs to branch on the result. It leaves the meaning of PARTIAL and the needed state of the target store (app closed, permissions) implicit, which is the remaining gap for a 2-parameter diagnostic.

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 both target_path and the schema_mode enum are already documented in the schema; that sets the baseline at 3. The description corroborates the accepted input shapes (folder or .log/.ldb file) but adds no semantics for the schema_mode values chatsvc or generic-json, and gives no formatting or path-resolution hints 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 names a specific verb-and-resource pair: a read-only diagnostic and GO/PARTIAL/NO_GO feasibility check over a local Chromium/Electron IndexedDB/LevelDB directory or .log/.ldb file. The tender list (VS Code, Slack, Teams, Discord, WhatsApp Desktop) pins down the artifact domain. It does not name or contrast with any sibling tool, which keeps it just shy of a 5.

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 framing as a 'precheck' and 'feasibility check' implies this is a preflight step taken before full extraction, so the gating context is readable. However, the description never states when it should not be used, does not name an alternative tool for the actual extraction, and does not mention prerequisites such as needing a closed/locked store or the app not running. Usage is implied rather than prescribed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.