Skip to main content
Glama

prepare_committee

Prepares deterministic market data blocks and role instructions so an agent can run the four-role investment committee itself, then submit the full transcript for review.

Instructions

Step 1 of the agent-run committee (Coordinator path): get everything YOU need to play the 4 roles yourself — no backend LLM key involved.

Returns the deterministic data blocks (regime, sentiment / defense flag, valuation, macro, events, portfolio, path reference) plus the 6 role prompts and instructions describing the 3 rounds. Run Macro / Quant / Risk (cheap subagents are fine), write the CIO memo yourself, then call submit_committee with the full transcript.

The backend keeps its own copy of the deterministic facts from this call and uses them when you submit (defense downgrade, regime, path snapshot), so a fact you forget to paste cannot silently switch a rule off. Submit within 6 hours of preparing.

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": "prepare_committee"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoActual model or fixed role-model composition; unknown disables model-specific prior insights.
symbolYesA symbol already in strategy target_assets, e.g. 'GC=F', 'NDQ.AX'.
providerNoActual reasoning host, needed to scope learned evidence.agent

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.68.4
    • addedInput schema / properties / model
      Added value: +{
      +  "default": "",
      +  "description": "Actual model or fixed role-model composition; unknown disables model-specific prior insights.",
      +  "title": "Model",
      +  "type": "string"
      +}
    • addedInput schema / properties / provider
      Added value: +{
      +  "default": "agent",
      +  "description": "Actual reasoning host, needed to scope learned evidence.",
      +  "title": "Provider",
      +  "type": "string"
      +}
  2. Addedv0.45.1

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly=false, idempotent=false, destructive=false) by disclosing that the backend retains its own copy of the deterministic facts and reuses them at submit time, preventing a forgotten fact from silently disabling a rule. It also states the 6-hour submission deadline and that no backend LLM key is consumed — operational facts an agent cannot infer from structured fields.

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-loads the role and return payload before the procedural instructions and the safety note, and every sentence carries actionable information. Slightly verbose in the parenthetical asides (e.g. 'cheap subagents are fine'), but nothing is genuinely wasteful.

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 carries the return-value burden and does so by enumerating the data blocks and prompts returned. It also covers the downstream submit contract and the expiry window, so an agent has everything needed to call it and continue the workflow 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 all three parameters (model, symbol, provider) are already documented in the schema. The description adds no further meaning about their formats or interactions, so the baseline of 3 applies.

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?

Names the specific verb and lifecycle position ('Step 1 of the agent-run committee (Coordinator path)') and enumerates exactly what is returned: deterministic data blocks, 6 role prompts, and round instructions. It is clearly distinguishable from siblings run_committee and submit_committee, which appear by name or by the named next step.

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 a clear selection condition — use this when you want to run the 4 roles yourself with 'no backend LLM key involved' — and prescribes the follow-on sequence (run Macro/Quant/Risk, write CIO memo, then call submit_committee). It does not explicitly name run_committee as the alternative path for the backend-LLM case, leaving that contrast implicit rather than stated.

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