Skip to main content
Glama

pacifica_vaults

Inspect Pacifica vault metrics like TVL, NAV, fees, and lock-up details, plus linked account equity, positions, and withdrawal status. Read-only data access for vault analysis.

Instructions

Pacifica vaults (API: lakes), read-only. Without vault: every vault (TVL, NAV per share, fee, lock-up, withdrawal window, config); with account: plus that account's shares. With vault (address, or a nickname matching exactly one vault — an ambiguous nickname is INVALID_PARAMS listing the candidates): one vault plus live account equity, positions, deposit whitelist (unofficial endpoint, advisory) and whether withdrawals are open now. APY is not published (null). Deposits / withdrawals are CLI-only: perp -e pacifica vault deposit|withdraw (supports --dry-run).

Input Schema

NameRequiredDescriptionDefault
vaultNoVault address or exact nickname
accountNoInclude this account's shares

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.16.0
    • removedInput schema / properties / account / pattern
      Removed value: -"^[1-9A-HJ-NP-Za-km-z]{32,44}$"
  2. Addedv0.15.0

TDQS

A4.7/5.0
Behavior5/5

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

No annotations are present, so the description carries the full burden; it discloses read-only behavior, the unofficial/advisory deposit whitelist endpoint, that APY is null, and that mutations are CLI-only. It also explains error behavior for ambiguous nicknames and what data is returned in each mode.

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?

The description front-loads read-only vault access and packs the relevant mode distinctions into a compact paragraph. It is dense with parenthetical details and semicolons, so it is efficient but not maximally readable.

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?

Given no annotations and no output schema, the description does a lot: it names returned fields per mode, flags APY as null, and routes write operations to the CLI. The remaining gap is the exact account-plus-vault return behavior.

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 100%, so baseline is 3, but the description adds useful semantics: vault accepts an address or exact nickname and ambiguous nicknames are rejected with candidates. It explains account as adding the account's shares, though the interaction between vault and account in vault mode is slightly under-specified.

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 the resource (Pacifica vaults, API lakes) and the read-only retrieval operation directly, and distinguishes the three modes by whether vault/account are supplied. An agent can identify it as the vault-data tool, separate from balance, position, and order siblings.

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?

Explicitly describes when each mode applies: no vault lists every vault, account adds shares, and vault returns one vault with live details. It also warns that deposits/withdrawals are CLI-only and that ambiguous nicknames produce INVALID_PARAMS, giving clear when-not guidance.

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