Skip to main content
Glama

AINDEX

Make a new agent with its own wallet

create_agent

Make one of the owner's agents: it gets its own wallet on Robinhood Chain, owned by the owner's AINDEX sign-in, and trades on Lighter and Robinhood Chain as its strategy says. Before calling, show the person the plan (plan_agent) and confirm the name and the strategy. It trades on its own and reports after each trade. It thinks with this app (thinks_with "your_ai", the default: no model cost, its checks run here with schedule_checks) unless the person asks for a model AINDEX runs on credits ("aindex"; about_agents lists them and their prices). Answers with the wallet address to fund and what to do next. Needs this chat connected (connect_account) with Run my agents.

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": {
      "name": "<name>"
    },
    "name": "create_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe agent's name.
modelNoWith thinks_with aindex: the model id, as about_agents lists it (e.g. ~anthropic/claude-sonnet-latest).
followNoMake a copy instead: the id of a public agent to copy, or any Hyperliquid account's address (0x...) to copy that trader. The copy mirrors its trades with its own money, needs no AI and pays no credits; AI can be added later on the website.
strategyNoWhat it should do, in the owner's words: markets, sizes, risk, when to act. Not needed with follow.
asks_firstNoLeave out: agents trade on their own and report after each trade. true is an older mode, kept only for the person who asks for it by name.
thinks_withNoyour_ai (default): this app thinks for it. aindex: only if the person asks for a model AINDEX runs, paid from credits. code: no AI at all; the person's own code or this app drives it with call_agent_tools, and its strategy runs every minute.your_ai
every_minutesNoHow often it checks, in minutes. Leave out for the usual schedule.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only say it is a non-read-only, non-destructive, non-idempotent local write; the description adds the important behavior: creation implies a repeatable new entity each call, the agent trades on its own and reports after each trade, and credits are only spent in 'aindex' mode. It also discloses the return shape (wallet address to fund, next steps). Minor gap: no statement about failure or partial-creation behavior.

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?

Front-loaded with the core action and side effects, then prerequisites, then parameter guidance; each sentence carries distinct information. It is dense and parenthetical-heavy, with a few clauses that read as run-on, but nothing is clearly wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a seven-parameter creation tool with no output schema, the description covers prerequisites, the pre-call confirmation flow, autonomous post-creation behavior, cost model, and the returned wallet address and next step. An agent has enough to call it correctly and set expectations with the user.

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 every parameter including 'follow', 'thinks_with', 'asks_first', and 'every_minutes' is already documented in the schema. The description mostly restates the model-selection tradeoff (your_ai vs aindex credits) rather than adding new semantics, so it earns the baseline for a fully documented schema.

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 and resource ('Make one of the owner's agents') plus the concrete side effects: a dedicated wallet on Robinhood Chain, ownership via the AINDEX sign-in, and autonomous trading on Lighter and Robinhood Chain. This is clearly distinguishable from siblings like update_agent, plan_agent, and list_agent_proposals.

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?

Gives explicit prerequisites ('Needs this chat connected (connect_account) with Run my agents') and an ordering rule ('Before calling, show the person the plan (plan_agent) and confirm the name and the strategy'). It also routes the model choice: default thinks_with 'your_ai' unless the person asks for a credits-charged model, with about_agents named as the lookup.

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