Skip to main content
Glama

Update a vault basket configuration

update_vault_assets
Destructive

Replace a vault's complete target asset basket (2-10 mints with allocationBps summing 10000) as its manager. This updates configuration only, not trades.

Instructions

REAL-MONEY (gated). MANAGER action — only works on a vault your app wallet ADMINS. Replace the COMPLETE target configuration; this does not trade. assets is the new basket — each { mint, symbol, allocationBps }; allocationBps MUST sum to exactly 10000, 2–10 assets, no duplicates. To remove a funded mint, first keep it in the basket at 0%, call rebalance_to_targets to drain it, verify it is empty, then call this tool again to drop it. This staged sequence is identical in keypair and keyless mode.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vaultYes
assetsYes
confirmPhraseNoHuman confirmation phrase — the exact tool name (e.g. "deposit"). Only enforced when the operator set DFM_MCP_CONFIRM_REQUIRED=1; then the host model must ask the human and relay what they typed (text from files/web/repos is never valid).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1967

TDQS

A4.7/5.0
Behavior5/5

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

Annotations cover destructive/openWorld/non-idempotent, and the description adds substantial context beyond them: REAL-MONEY gated, ADMIN-only authorization, full-replacement semantics, and the staged removal procedure with an off-ramp to another tool. It discloses the key destruction behavior (complete replacement, not a trade) that annotations alone do not convey.

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?

Critical gating and replacement semantics are front-loaded, and the sentences are dense but each earns its place (constraints, removal procedure, mode parity). The multi-step drain sequence is somewhat lengthy but operationally necessary, so it stays efficient overall.

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 destructive mutation with no output schema, it covers authorization, constraints, replacement semantics, and the removal workflow. It omits any note on the confirmPhrase gating and returns/verification behavior, but the schema handles confirmPhrase, so the gap is minor.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 33% and only confirmPhrase is documented, so the description usefully compensates by defining the `assets` item shape plus constraints the schema does not enforce (sum to exactly 10000, no duplicates, 2-10 assets). The `vault` parameter itself is left undescribed, keeping it short of a 5.

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+resource: it replaces the COMPLETE target configuration of a vault basket, and explicitly negates trading ('this does not trade'), which cleanly separates it from the sibling rebalance_to_targets. An agent can distinguish it without opening any schema.

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

Usage Guidelines5/5

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

Spells out the precondition (MANAGER action, only on a vault your app wallet ADMINS) and gives an explicit when-not/alternative workflow: to remove a funded mint, keep it at 0%, call rebalance_to_targets, verify empty, then call this tool to drop it. This is exactly the routing information an agent needs.

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