Skip to main content
Glama

run_committee

Idempotent

Analyze a symbol with a four-role LLM investment committee that debates evidence and returns a calibrated BUY/HOLD/SELL verdict with a written CIO memo.

Instructions

Run the 4-role LLM investment committee on a symbol (Direct path): Macro Strategist, Quant Analyst, and Risk Officer debate from isolated evidence, then a CIO synthesizes one calibrated BUY/HOLD/SELL-style verdict with a written memo.

Requires a backend LLM key (e.g. DEEPSEEK_API_KEY) and takes 30-90s on a cache miss. If the symbol was already analyzed today, the cached verdict is returned instantly unless force is set. Sends MCP progress notifications per debate phase when the client asks for them. Decision support only — the human always executes.

Args: symbol: Symbol to analyze. Listed assets use yfinance tickers: US "AAPL", A-share "603083.SS" (Shanghai) / "000001.SZ" (Shenzhen), HK "0700.HK", exchange ETF "510300.SS", crypto "BTC-USD", futures "GC=F". China off-exchange (OTC) mutual funds use "FUND:<6-digit code>", e.g. "FUND:110011". A bare 6-digit code is rejected — add the suffix or the FUND: prefix. force: Re-run even if a verdict already exists for today. max_rounds: Cross-challenge debate rounds (default 1).

Returns: Object with decision_id, cached flag, verdict and confidence_lookup (show this to the user instead of the self-reported confidence). The shape differs by path: - cached: false (fresh run): verdict is an object (verdict, confidence, suggested allocation, ...). - cached: true (today's transcript): verdict is the verdict string, with confidence, alloc_cny, alloc_currency alongside, plus the CIO memo as cio_memo and the deterministic input_health block (empty inputs, rewrite rules applied, forced HOLD) — no need to call explain_decision just to read them.

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": {
      "symbol": "<symbol>"
    },
    "name": "run_committee"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNoRe-run even if a verdict already exists for today.
symbolYesSymbol to analyze. Listed assets use yfinance tickers: US 'AAPL', A-share '603083.SS' (Shanghai) / '000001.SZ' (Shenzhen), HK '0700.HK', exchange ETF '510300.SS', crypto 'BTC-USD', futures 'GC=F'. China off-exchange (OTC) mutual funds use 'FUND:<6-digit code>', e.g. 'FUND:110011'. A bare 6-digit code is rejected — add the suffix or the FUND: prefix.
max_roundsNoCross-challenge debate rounds.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.68.1
    • changedInput schema / properties / symbol / description
      Previous value: -"Any yfinance ticker (US / HK / A-share / ETF / crypto / commodities), e.g. 'AAPL', 'GC=F', '510300.SS'."New value: +"Symbol to analyze. Listed assets use yfinance tickers: US 'AAPL', A-share '603083.SS' (Shanghai) / '000001.SZ' (Shenzhen), HK '0700.HK', exchange ETF '510300.SS', crypto 'BTC-USD', futures 'GC=F'. China off-exchange (OTC) mutual funds use 'FUND:<6-digit code>', e.g. 'FUND:110011'. A bare 6-digit code is rejected — add the suffix or the FUND: prefix."
  2. Addedv0.34.0
  3. Removedv0.31.6
  4. Changed4 schema fields changedv0.31.4
    • addedInput schema / properties / force / description
      Added value: +"Re-run even if a verdict already exists for today."
    • addedInput schema / properties / max_rounds / description
      Added value: +"Cross-challenge debate rounds."
    • addedInput schema / properties / max_rounds / minimum
      Added value: +1
    • addedInput schema / properties / symbol / description
      Added value: +"Any yfinance ticker (US / HK / A-share / ETF / crypto / commodities), e.g. 'AAPL', 'GC=F', '510300.SS'."
  5. First observedv0.31.0

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past annotations: discloses the hard dependency on a backend LLM key, the 30-90s cache-miss latency, caching semantics keyed to the day plus `force`, and streaming progress notifications per debate phase. It also adds a safety framing ('Decision support only — the human always executes') and warns that `confidence_lookup` should supersede the self-reported confidence, which the annotations say nothing about.

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?

Purpose and latency/caching caveats are front-loaded in the first two paragraphs, and the Args/Returns structure is easy to scan. It is somewhat long and the Args block duplicates schema text that is already 100% covered.

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?

Covers everything an agent needs before calling: symbol formatting edge cases (bare 6-digit code rejected, FUND: prefix), auth dependency, latency, cache-busting, and the fact that the return shape differs between cached:false and cached:true including the input_health block. Even with an output schema present, the path-dependent shape difference is essential context that the schema alone would not convey.

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 coverage is 100%, so every parameter is already documented; the description's Args block largely restates the symbol and force text verbatim and adds only the effective default for max_rounds. A baseline 3 is appropriate when the schema carries the full parameter burden.

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?

Names a specific verb and resource ('Run the 4-role LLM investment committee on a symbol') and spells out the roles and the output (a CIO-synthesized BUY/HOLD/SELL memo). The '(Direct path)' label hints at a staged alternative but never names prepare_committee/submit_committee, so sibling differentiation is implied rather than explicit.

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?

Gives clear operating context: a backend LLM key is required, a fresh run takes 30-90s, and today's cached verdict is returned unless `force` is set. It also steers the agent away from a sibling ('no need to call explain_decision just to read them'). What's missing is an explicit statement of when to prefer the staged/alternate committee path over this direct one.

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