Skip to main content
Glama

submit_committee

Idempotent

Submit an agent-run committee transcript so OpenInvest parses the CIO memo, applies deterministic investment rules, saves the decision, and returns the verdict.

Instructions

Step 2 of the agent-run committee: hand in the transcript you produced from prepare_committee. The backend parses the CIO memo, applies the same deterministic rules as the backend-run committee (single-investment cap, defense downgrade, sanity checks), saves the decision and returns it.

If the CIO section has no parseable verdict, nothing is saved and this returns an error — fix the CIO section and submit again.

Returns: decision_id, the post-rule verdict object, saved path and facts_source ("prepare" = rules used the facts saved at prepare time; "transcript" = no recent prepare found, facts were read from your text).

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>",
      "transcript": "<transcript>"
    },
    "name": "submit_committee"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoModel that actually played the roles, e.g. 'claude-sonnet-5-5'; omitted -> recorded as 'unknown'. The scorecard buckets verdicts by provider:model.
symbolYesSame symbol you passed to prepare_committee.
providerNoWhich agent played the roles, e.g. 'hermes', 'claude', 'codex'.agent
context_idNoExact context_id returned by prepare_committee; required to bind inputs and rules to this submission.
transcriptYesAll sections, each starting with its separator line: === MACRO ===, === QUANT_R1 ===, === RISK_R1 ===, === QUANT_R2 ===, === RISK_R2 ===, === CIO ===.
reasoning_review_jsonNoIndependent review JSON for the exact verification_request returned by an earlier submission; submit the unchanged original transcript. Omit for the first submission.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.68.10
    • addedInput schema / properties / reasoning_review_json
      Added value: +{
      +  "default": "",
      +  "description": "Independent review JSON for the exact verification_request returned by an earlier submission; submit the unchanged original transcript. Omit for the first submission.",
      +  "title": "Reasoning Review Json",
      +  "type": "string"
      +}
  2. Changed1 schema field changedv0.68.4
    • addedInput schema / properties / context_id
      Added value: +{
      +  "default": "",
      +  "description": "Exact context_id returned by prepare_committee; required to bind inputs and rules to this submission.",
      +  "title": "Context Id",
      +  "type": "string"
      +}
  3. Addedv0.45.1

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true), it discloses what the backend actually does: parses the CIO memo, applies deterministic rules (single-investment cap, defense downgrade, sanity checks), and persists a decision. It also describes the failure mode precisely — no parseable verdict means nothing is saved — and explains what `facts_source` means for outcome interpretation.

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 step position and the core action are front-loaded, and the returns block is clearly separated. Minor waste remains: the 'Returns:' list restates fields an output schema already covers, and the error condition is mentioned twice in close succession.

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 mutating, rules-applying submission with an output schema already present, the description covers everything an agent needs: prerequisite, failure and retry behavior, side effects on persistence, and the meaning of the returned provenance flag. Nothing needed to call it correctly is missing.

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 the baseline is 3; the description earns an extra point by explaining the consequence of `context_id` binding through `facts_source` ('prepare' vs 'transcript') and by clarifying that `reasoning_review_json` must be paired with the unchanged original transcript. It does not add syntax-level detail for `transcript` beyond what the schema lists.

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?

The description uses a specific verb and resource ('hand in the transcript') and anchors itself positionally ('Step 2 of the agent-run committee') against the named sibling `prepare_committee`, whose output it consumes. An agent can distinguish this submission step from the preparation step without opening either schema.

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 states the prerequisite chain (transcript produced from `prepare_committee`), the recovery path on failure ('fix the CIO section and submit again'), and a conditional rule for the optional review parameter ('Omit for the first submission'). It stops short of explicitly contrasting with backend-run alternatives such as `run_committee` or `committee_review`, so no full when-not guidance is given.

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