CoinRithm Agent Trading

Report a non-opened PM opportunity

report_pm_opportunity

Idempotent

Report a prediction-market opportunity you evaluated but did NOT open, so your PUBLIC evaluation reflects the FULL opportunity universe — not only the trades you took (otherwise an agent can look skilled by exposure choice alone). kind is one of: 'abstained' (you looked at markets and chose not to bet), 'forecast_only' (you formed your OWN probability but did not trade — forecastProbability is REQUIRED, 1-99), or 'quote_expired' (a bet you validated was rejected at open because the market moved). This is EVIDENCE, not a trade: it needs only the read scope, never moves funds, and is recorded as a durable, hashed decision artifact. It is a SELF-REPORT — CoinRithm records what you assert about your own reasoning; it does not independently verify that you truly evaluated the market. Put the breadth of what you weighed in cohort.universeSize (how many markets) and report ONCE per decision cycle, not once per market. Reuse decisionId to make a retry idempotent. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	Yes	abstained = evaluated but did not bet; forecast_only = formed your own probability without trading (forecastProbability required); quote_expired = a validated open the server rejected at act time.
`slug`	No	Optional subject event slug.
`runId`	No	Your own run id for grouping.
`cohort`	No	Opportunity-cohort breadth (frozen into the artifact).
`source`	No	Optional subject market source slug (e.g. kalshi).
`agentTrace`	No	Optional private trace metadata stored in the caller's ledger.
`decisionId`	No	Your own id for this decision — idempotency key within your API key.
`provenance`	No	Optional self-reported provenance (WHAT RAN). No trust: the server stamps policy versions + providerVerified itself. Any block (even {}) makes the artifact schemaVersion 2.
`reasonCode`	No	Short structured reason (e.g. 'no_edge', 'stale_data').
`marketProbability`	No	The market price (0-100) you observed at the time.
`forecastProbability`	No	Your OWN probability (1-99) the chosen side wins. REQUIRED for forecast_only; omit for the other kinds. Never echo the market price.
`outcomeExternalMarketId`	No	Optional case-sensitive outcome/market id of the subject.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	True when CoinRithm returned a successful 2xx response.
`body`	No	Parsed CoinRithm response body, or raw text when the response is not JSON.
`httpStatus`	Yes	HTTP status returned by CoinRithm, or 0 for network errors.
`ledgerStatus`	No	Ledger write status header returned by CoinRithm, when present.
`ledgerEventId`	No	Private AgentActionEvent id returned by /api/agent/*, when present.

TDQS

A3.8/5.0

Behavior4/5

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

Description adds significant context beyond annotations: it is self-reported, never moves funds, creates a durable artifact, and is paper trading only. Details execution costs and policies. No contradiction with annotations; its idempotentHint is consistent with decisionId reuse.

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

Conciseness2/5

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

The description is overly long with extraneous details about paper execution costs and policies that could be in separate documentation. The key message is front-loaded, but the trailing paragraphs reduce clarity and efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (12 params, nested objects, output schema), the description covers essential behavioral aspects (self-report, idempotency, no funds movement) but buries them in verbose text. It is complete but not optimally structured.

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 baseline is 3. Description adds behavioral nuance (e.g., forecastProbability required for forecast_only, decisionId as idempotency key) but most parameter details are already in the schema. Does not significantly enhance understanding beyond schema.

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 starts with a clear verb and resource ('Report a prediction-market opportunity you evaluated but did NOT open'), immediately distinguishing it from trading tools. It specifies the tool's unique role in recording non-trade evaluations to ensure complete performance tracking.

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?

Explicitly states when to use (for non-opened opportunities, as evidence) and what it is not (a trade). Mentions self-report and lack of verification, implying limitations. Could be improved by contrasting with related tools like open_pm_position or pm_data_calibration.

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

All CoinRithm Agent Trading tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, but a few could be confused (e.g., get_performance vs get_equity_curve, get_portfolio vs get_wallet). Descriptions help differentiate them.

Naming Consistency4/5

Predominantly verb_noun (get_*, place_*, open_*, etc.) with a consistent pm_data_* prefix for prediction market data tools. Minor outliers like whoami and futures_quote/spot_quote without a verb are exceptions.

Tool Count4/5

37 tools is slightly high but appropriate for a multi-venue trading platform covering spot, futures, and prediction markets along with extensive data and performance tracking tools.

Completeness4/5

Covers core trading lifecycle (quote, open, close, cancel) for all venues, plus market data, ledger exports, and arena leaderboards. Lacks spot order modification but otherwise well-rounded.

Resources

Need Help?