Skip to main content
Glama
starshield-forensics

starshield-forensics

by Ziqi

Inspect PNG/JPEG Screenshot & Receipt Container Provenance

starshield_inspect_image_tamper
Read-onlyIdempotent

Verifies PNG chunk CRC32 and JPEG ICC/Photoshop resource integrity to pre-screen receipts, reimbursement images, and disputed screenshots for tampering.

Instructions

Deterministically verify RFC 2083 PNG chunk CRC32 integrity (IHDR/IDAT/IEND/iCCP) and ISO 10918 JPEG APP2 ICC_PROFILE / APP13 Photoshop 8BIM resource blocks for FinTech reimbursement, e-commerce receipt, and disputed screenshot pre-screening.

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": {
      "image_path": "<image_path>"
    },
    "name": "starshield_inspect_image_tamper"
  }
}

Input Schema

NameRequiredDescriptionDefault
image_pathYesLocal path to a PNG or JPEG screenshot, receipt, or attachment.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety and determinism profile is largely covered; 'deterministically' reinforces this. What is missing is behavior beyond the checks themselves: whether it reports a tamper verdict, how findings are graded, and whether a non-PNG/JPEG or malformed file is an error or a negative result.

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 with no filler, and the verification target leads. It is dense to the point of being hard to parse on first read (stacked spec numbers and chunk names), and the three-way use-case list overlaps somewhat, costing it a point.

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

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of explaining what comes back — but it says nothing about the return shape or whether an overall tamper/integrity verdict is produced. The tool name promises tamper inspection while the description only commits to chunk and resource-block integrity verification, leaving a meaningful gap for an agent deciding whether this answers a tampering question.

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% and the single parameter is fully described in the schema ('Local path to a PNG or JPEG screenshot, receipt, or attachment'), which the description largely restates. No extra meaning is added, such as accepted extensions, handling of relative vs absolute paths, or size limits, so the 3 baseline 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?

States a specific verb ('deterministically verify') against named artifacts ('RFC 2083 PNG chunk CRC32 integrity (IHDR/IDAT/IEND/iCCP)' and 'ISO 10918 JPEG APP2 ICC_PROFILE / APP13 Photoshop 8BIM resource blocks'). The subject matter is technical but unambiguous, and it is clearly distinct from the sibling tools (demo, precheck_leveldb, validate_financial_iocs).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The trailing clause names concrete usage contexts — FinTech reimbursement, e-commerce receipt, and disputed screenshot pre-screening — which tells an agent when this tool fits. It stops short of any explicit exclusions or named alternatives for adjacent tasks (e.g., when to prefer validate_financial_iocs instead).

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