Skip to main content
Glama
Sign In

SimianX AI

by io.github.SimianX-AI
OverviewDiscussionsAdmin

Start a live analysis session

start_live_session

Watch a symbol while the user talks to you: the four live agents run at every candle close of the timeframe and report fundamentals, technicals, news flow and the decision with the next run time, for as long as you keep following (get_updates every 10 s, or the WebSocket). The session ends two minutes after you stop following; an autopilot keeps going offline. After starting, follow it until done and tell the user every finished step; never wait for the user to ask. (uses points, metered on the models used like the website)

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": {
      "asset": "<asset>",
      "symbol": "<symbol>"
    },
    "name": "start_live_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNoModel tier (default fast)
assetYescrypto or stock (US stocks and ETFs)
agentsNoSubset of the four live agents (default all four)
modelsNoPer-agent model override, agent -> model id from list_models (paid plans)
symbolYesStock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP
languageNoLanguage of the write-ups, e.g. en, zh-CN, ja (default: the account's)
timeframeNoCandle timeframe. Crypto: 1m 5m 15m 1H 4H 1D. Stock: 1m 15m 1H 1D 1W 1mo. Default 15m

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations, the description discloses the session lifecycle, the two-minute termination after the agent stops following, the autopilot exception, the polling cadence, and that usage is metered in points. These are exactly the behavioral details an agent needs before starting a non-idempotent live session.

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 purpose is front-loaded and every sentence carries operational meaning, including the follow-up instructions and the cost note. It is dense, with a long compound sentence and parenthetical billing note, but not padded.

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?

With no output schema, the description explains what the session reports and how to receive it via get_updates or WebSocket, as well as when the session ends. It covers the lifecycle, monitoring, and cost considerations needed to invoke and manage the tool correctly.

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 schema already documents all seven parameters, including enums, defaults, and the nested per-agent model override. The description adds only a light mapping to the four live agents and the points cost, without clarifying tier, timeframe, or language beyond what the schema already says.

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 description states a specific action and resource: start a live session that watches a symbol while the user talks, with four agents reporting at candle closes. It is clearly distinguishable from list/get/stop siblings, but it does not explicitly distinguish itself from run_live_analysis or autopilot workflows.

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?

It gives strong operational guidance: follow with get_updates every 10 seconds or the WebSocket, follow until done, and never wait for the user to ask. It lacks explicit when-not-to-use guidance versus alternatives such as run_live_analysis or create_autopilot, though the autopilot note implies a boundary.

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

All SimianX AI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources