Skip to main content
Glama
Sign In

JW3 MCP Server

by io.github.agnostic4321-ops
OverviewDiscussionsAdmin

Propose prediction trade

propose_predict_market

APPROVAL CARD ONLY — NEVER auto-executed: propose a prediction-market trade for in-app approval. JEV-gated: pass the consult_jev family=prediction verdict (run analyze_market first) — a call without one is refused. Recorded as a proposal trail row. Never executes, never moves funds. Needs the trade:propose scope (PAT).

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": {
      "market_id": "<market_id>",
      "side": "<side>",
      "rationale": "<rationale>",
      "jev_verdict": "<jev_verdict>"
    },
    "name": "propose_predict_market"
  }
}

Input Schema

NameRequiredDescriptionDefault
sideYesOutcome to buy
venueNoDefault polymarket (executable). opinion is proposal-only.
amountNoOptional pUSD amount to spend (must be > 0 when provided)
questionNoOptional human-readable question, for UI display
market_idYesPolymarket conditionId or slug, or Opinion market id
rationaleYesWhy this market and side now
confidenceNoOptional agreement-weighted conviction 0–1
jev_verdictYesThe consult_jev family=prediction verdict (run analyze_market first) — required

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that it writes a proposal trail row, requires the trade:propose PAT scope, is gated on a JEV verdict and refuses calls lacking one, and never moves funds. The annotations (readOnlyHint=false, destructiveHint=false) are consistent with a non-destructive write that only records a proposal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense paragraph with the safety guarantee front-loaded, then gates, then side effects, then auth. Every clause carries operational information; nothing is redundant with the title alone.

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 an 8-param, non-destructive-but-mutating proposal tool with no output schema, the description covers safety, prerequisites, persistence semantics, and required scope — everything an agent needs before calling it 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 parameters like side, venue, amount, and confidence are already documented. The description reinforces the jev_verdict provenance (analyze_market / consult_jev) but that fact is also in the schema's own description, so it adds little new param-level meaning.

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 ('propose a prediction-market trade for in-app approval') plus a hard scope marker ('APPROVAL CARD ONLY — NEVER auto-executed'), which cleanly separates it from execute_trade and from the generic propose_trade sibling without needing their schemas.

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 concrete prerequisite chain: run analyze_market first, then pass the consult_jev family=prediction verdict, and warns that calls without one are refused. It doesn't explicitly route the agent elsewhere when it actually wants execution (e.g., execute_trade), relying on 'never executes' to imply that.

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

All JW3 MCP Server 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