Skip to main content
Glama
Sign In
Privacy-Scan

Privacy-Scan

by Nymrasi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Nymra fix plan

fix_plan
Read-onlyIdempotent

Generates a wallet privacy remediation plan from a 0x address or ENS name: shows leaks you can undo, score points recovered, future steps, and permanent on-chain exposure.

Instructions

The Nymra fix plan for an EVM wallet: what its owner can undo today and how many points of the Privacy Score that wins back, what to do differently from now on, and what is on chain for good, with who can see each leak and the steps to take. Give a 0x address or an ENS name. Uses a scan of the last ten minutes, or runs one.

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": {
      "wallet": "<wallet>"
    },
    "name": "fix_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
walletYesOne EVM wallet: a 0x address with 40 hex characters, or an ENS name such as vitalik.eth.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds genuinely new behavior: it reuses a scan from the last ten minutes or triggers a fresh one, which tells the agent about freshness and possible latency/cost of a cold call. It also enumerates what the plan contains, including per-leak visibility and the concrete steps to take. It stops short of saying what happens when no scan exists or whether results are cached per wallet.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The input instruction is front-loaded only after a very long, comma-chained first sentence that packs four distinct concepts into one clause. Every idea is relevant, but the dense enumeration makes the key action ('give a wallet, get a fix plan') harder to extract at a glance. Trimming or splitting the opening clause would improve scannability.

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?

There is no output schema, so the description must carry the return-value burden, and it does: it names the plan's sections (undoable now, points of Privacy Score regained, going-forward changes, permanent on-chain exposure, who can see each leak, steps). The scan-reuse behavior is also disclosed. Only minor gaps remain, such as failure modes for unknown wallets or whether the plan is returned as text or structured sections.

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?

With a single parameter at 100% schema coverage, the schema already documents the 0x/ENS acceptance rule in full. The description restates the same rule ('Give a 0x address or an ENS name') without adding format edge cases, resolution behavior for ENS, or validation failures. Baseline 3 applies since the schema carries the parameter meaning.

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 states a concrete deliverable for a concrete resource: a remediation plan for one EVM wallet, broken into what can be undone now, what to change going forward, and what is permanently on chain. It is output-oriented rather than verb-first, but an agent can tell it produces an actionable plan rather than raw findings. It hints at the sibling relationship ('Uses a scan of the last ten minutes, or runs one') without naming scan_wallet directly.

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: the agent learns it needs a wallet identifier and that a recent scan is reused or a new one is run. There is no explicit statement of when to pick this over scan_wallet, nor any exclusion or prerequisite (e.g. whether an unindexed wallet still works). Adequate but leaves the routing decision to inference.

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