Skip to main content
Glama
Sign In
Agentic AQUA

Agentic AQUA

Official
by AquaWallet
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

lw_backup_mnemonic

Writes a wallet's seed phrase to a local plain-text backup file when the user explicitly requests a backup. Keeps the mnemonic out of the conversation while preserving a recoverable copy.

Instructions

Write the wallet's seed to a local plain-text backup file. Call ONLY when the user explicitly asks to back up the seed. The seed is never returned; never read the file back into the conversation.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "lw_backup_mnemonic"
  }
}

Input Schema

NameRequiredDescriptionDefault
passwordNoPassword to decrypt the mnemonic (if encrypted at rest)
wallet_nameNoWallet to back updefault
password_fileNoPath to a local file containing the wallet password; keeps the password out of the conversation. Do not combine with password.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses that the output is an unencrypted local file, that the seed is never returned in the response, and that the file must not be read back into the conversation. It omits where the file is written, whether an existing backup is overwritten, and whether a password is mandatory — details that matter for a destructive-ish write.

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

Conciseness5/5

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

Three short sentences, no filler, and the safety gate is placed immediately after the purpose statement. The final sentence pairs the 'never returned' guarantee with the 'never read back' rule efficiently.

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?

For a no-annotation, no-output-schema tool handling a seed, the description covers intent and conversational handling well but leaves out operational facts an agent would need to answer follow-ups: destination path, overwrite behavior, and required permissions. Adequate but not complete for the sensitivity of the operation.

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 all three parameters (password, wallet_name, password_file, including the mutual-exclusion note) are already documented in the schema. The description adds no parameter-level meaning beyond that, which is the baseline case for fully documented schemas.

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 verb and resource are concrete: write the wallet's seed to a local plain-text backup file. An agent can distinguish this from lw_import_mnemonic (inbound) and lw_export_descriptor (descriptor, not seed) by the stated artifact, though no sibling is named explicitly.

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?

A hard gating condition is stated: 'Call ONLY when the user explicitly asks to back up the seed,' which is exactly the right exclusion for a high-risk operation. It stops short of naming alternatives (e.g., descriptor export for watch-only setups), so it is clear context without full alternative routing.

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