Skip to main content
Glama

vault_copy

Set what a shared vault copies: one of the strategies measured on the time compressor (or "none" to stand aside), the book desk that trades it (its attribution on the Taifoon book; leave it out while the strategy has no desk and the vault stands aside), the ratio of that desk's position the vault holds, the most it may trade in one pass, and the markets. The vault's mirror reads this and brings the vault's venue account to desk position x ratio. Only the vault's administrators may set it (the house: people and the house agents acting for them); every mandate is kept, newest first.

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": {
      "vault": "<vault>",
      "strategy": "<strategy>",
      "ratio": "<ratio>",
      "max_usd_per_pass": "<max_usd_per_pass>",
      "markets": "<markets>"
    },
    "name": "vault_copy"
  }
}

Input Schema

NameRequiredDescriptionDefault
deskNothe book attribution of the desk that trades it (optional)
noteNowhy (optional, kept with the mandate)
ratioYesthe share of the desk's position the vault holds: in (0, 1] for real money, up to 10 on a test-money vault (a practice desk trades 5 USD, the venue's smallest order is 10)
vaultYesthe shared vault's id or address
marketsYesthe markets it copies
strategyYesa measured strategy id (strategies on the vault room's chooser) or "none"
max_usd_per_passYesthe most the mirror may trade in one pass

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / ratio / description
      Previous value: -"the share of the desk's position the vault holds, in (0, 1]"New value: +"the share of the desk's position the vault holds: in (0, 1] for real money, up to 10 on a test-money vault (a practice desk trades 5 USD, the venue's smallest order is 10)"
  2. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare it is a non-readonly, non-destructive, non-idempotent write; the description adds real context beyond that: admin-only authorization, the fact the vault's mirror reads the setting and brings the venue account to desk position x ratio, and that every mandate is kept newest-first as an audit trail. It does not state reversibility or what a failed call returns, but the added authorization and effect disclosure is substantial.

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?

Effectively two sentences, front-loaded with the core action and then the authorization/audit note. It is dense and jargon-heavy, and the parenthetical asides strain readability, but there is little outright waste.

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?

For a 7-parameter mutation with no output schema, the definition covers the effect (mirror sync to desk position x ratio), the authorization model, the sentinel value, and the audit retention. Missing only error/permission-failure behavior and whether re-setting replaces or supersedes the prior mandate, which the 'newest first' phrasing half-implies.

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 the baseline is 3. The description does clarify inter-parameter dependencies (desk is meaningless while the strategy has no desk; ratio above 1 only on test-money vaults) and the "none" sentinel for strategy, but most of its parameter talk restates what the schema already documents.

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+resource: "Set what a shared vault copies", followed by an enumeration of the configurable fields (strategy, desk, ratio, max pass size, markets). An agent can tell this configures a vault's mirror behavior, though the jargon ("time compressor", "Taifoon book") makes the object of the operation less immediately legible and it never names its sibling alternatives.

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?

Provides conditional guidance embedded in prose: use "none" to stand aside, leave the desk out while the strategy has no desk, and only administrators may set it. It offers no explicit comparison to siblings like vault_prepare or vault_join, so the agent must infer when this is the right call versus those.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources