Skip to main content
Glama

CoinRithm Agent Trading

Report a non-opened PM opportunity

report_pm_opportunity

Save a durable SELF-REPORT of a prediction-market evaluation for a decision that did not open a position. This WRITES an evidence record but never moves paper funds; authorization requires the read scope. It does not independently verify your evaluation. Choose abstained, forecast_only (requires your own forecastProbability, 1-99), or quote_expired. Report once per decision cycle; cohort.universeSize records its breadth. Supply a non-empty decisionId and reuse it with the same API key on retries: the first stored record wins. agentTrace.decisionId is a fallback; omitting both creates separate records. Success returns body.decisionUuid and, on replay, body.idempotentReplay=true. Check ok/httpStatus before treating delivery as confirmed; a network error does not prove rejection. Use open_pm_position to place a paper trade.

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": {
      "kind": "<kind>"
    },
    "name": "report_pm_opportunity"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesabstained = 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.
slugNoOptional subject event slug.
runIdNoYour own run id for grouping.
cohortNoOpportunity-cohort breadth (frozen into the artifact).
sourceNoOptional subject market source slug (e.g. kalshi).
agentTraceNoOptional private trace metadata stored in the caller's ledger.
decisionIdNoNon-empty id for this decision, unique within your API key. Reuse for retries. Falls back to agentTrace.decisionId; omitting both creates a new record on each call.
provenanceNoOptional self-reported provenance (WHAT RAN). No trust: the server stamps policy versions + providerVerified itself. Any block (even {}) makes the artifact schemaVersion 2.
reasonCodeNoShort structured reason (e.g. 'no_edge', 'stale_data').
marketProbabilityNoThe market price (0-100) you observed at the time.
forecastProbabilityNoYour OWN forecast probability (1-99). REQUIRED for forecast_only; optional for other kinds. Never echo the market price.
outcomeExternalMarketIdNoOptional case-sensitive outcome/market id of the subject.

Output Schema

NameRequiredDescriptionDefault
okYes
bodyNo
httpStatusYes
ledgerStatusNo
ledgerEventIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / cohort / properties / universeSize / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / provenance / properties / skillVersions / propertyNames
      Added value: +{
      +  "type": "string"
      +}
  2. Changed5 schema fields changed
    • removedOutput schema / properties / body / description
      Removed value: -"Parsed CoinRithm response body, or raw text when the response is not JSON."
    • removedOutput schema / properties / httpStatus / description
      Removed value: -"HTTP status returned by CoinRithm, or 0 for network errors."
    • removedOutput schema / properties / ledgerEventId / description
      Removed value: -"Private AgentActionEvent id returned by /api/agent/*, when present."
    • removedOutput schema / properties / ledgerStatus / description
      Removed value: -"Ledger write status header returned by CoinRithm, when present."
    • removedOutput schema / properties / ok / description
      Removed value: -"True when CoinRithm returned a successful 2xx response."
  3. Changed2 schema fields changed
    • changedInput schema / properties / decisionId / description
      Previous value: -"Your own id for this decision — idempotency key within your API key."New value: +"Non-empty id for this decision, unique within your API key. Reuse for retries. Falls back to agentTrace.decisionId; omitting both creates a new record on each call."
    • changedInput schema / properties / forecastProbability / description
      Previous value: -"Your OWN probability (1-99) the chosen side wins. REQUIRED for forecast_only; omit for the other kinds. Never echo the market price."New value: +"Your OWN forecast probability (1-99). REQUIRED for forecast_only; optional for other kinds. Never echo the market price."
  4. Changed1 schema field changed
    • addedInput schema / properties / provenance
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Optional self-reported provenance (WHAT RAN). No trust: the server stamps policy versions + providerVerified itself. Any block (even {}) makes the artifact schemaVersion 2.",
      +  "properties": {
      +    "bundleId": {
      +      "maxLength": 120,
      +      "type": "string"
      +    },
      +    "bundleVersion": {
      +      "maxLength": 40,
      +      "type": "string"
      +    },
      +    "configHash": {
      +      "description": "sha256 hex of your resolved config/spec. HASH ONLY — never raw text.",
      +      "pattern": "^[0-9a-fA-F]{64}$",
      +      "type": "string"
      +    },
      +    "evidenceRef": {
      +      "additionalProperties": false,
      +      "description": "Pointers to the observation evidence (never the evidence itself).",
      +      "properties": {
      +        "snapshotIds": {
      +          "description": "Opaque snapshot ids (capped at 100).",
      +          "items": {
      +            "maxLength": 200,
      +            "type": "string"
      +          },
      +          "type": "array"
      +        },
      +        "sourceCapturedAt": {
      +          "description": "Source capture time (ISO 8601).",
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "modelName": {
      +      "maxLength": 80,
      +      "type": "string"
      +    },
      +    "modelProvider": {
      +      "maxLength": 80,
      +      "type": "string"
      +    },
      +    "packageVersion": {
      +      "maxLength": 40,
      +      "type": "string"
      +    },
      +    "promptHash": {
      +      "description": "sha256 hex of your exact prompt strings. HASH ONLY — never raw text.",
      +      "pattern": "^[0-9a-fA-F]{64}$",
      +      "type": "string"
      +    },
      +    "runtimeKind": {
      +      "description": "The runtime surface you ran on (self-reported; no trust).",
      +      "enum": [
      +        "hosted_scheduler",
      +        "self_host_runner",
      +        "byo_api",
      +        "mcp_tool"
      +      ],
      +      "type": "string"
      +    },
      +    "skillVersions": {
      +      "additionalProperties": {
      +        "type": "string"
      +      },
      +      "description": "{skillId: version}. Capped: 50 keys, key<=120 / value<=40.",
      +      "type": "object"
      +    }
      +  },
      +  "type": "object"
      +}
  5. Added

TDQS

A4.8/5.0
Behavior5/5

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

Adds substantial behavior beyond annotations: it writes an evidence record but 'never moves paper funds', needs only the read scope, and 'does not independently verify your evaluation'. It also discloses idempotency semantics the annotations do not capture (first stored record wins per decisionId; omitting the id both times creates separate records) and cautions that 'a network error does not prove rejection' — a genuinely useful failure-mode note.

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?

Information-dense and front-loaded, with the write/scope/no-funds facts first and the sibling pointer last. It is slightly long for a description and repeats a couple of schema-stated rules (non-empty decisionId, agentTrace fallback), which costs it a point.

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 12-parameter tool with nested objects, this covers the essentials an agent needs: which kind to pick, what gets recorded, auth scope, retry/idempotency behavior, and the success signal. The output schema already defines return fields, so the brief mention of body.decisionUuid/body.idempotentReplay is a bonus rather than a necessity.

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, and much of the description's parameter detail (forecastProbability requirement, agentTrace.decisionId fallback) restates the schema. It does add operational meaning the schema lacks: the retry-with-same-decisionId convention and that non-empty ids are enforced per API key.

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 opening sentence states a specific verb and resource ('Save a durable SELF-REPORT of a prediction-market evaluation') and immediately scopes it to 'a decision that did not open a position', then names the counter-case sibling ('Use open_pm_position to place a paper trade'). An agent can separate this from open_pm_position and the pm_data_* readers without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit conditional routing: 'Choose abstained, forecast_only (requires your own forecastProbability, 1-99), or quote_expired', plus a frequency constraint ('Report once per decision cycle') and a direct alternative for the trading case. The only mild gap is that it does not say when NOT to report at all, but the 'non-opened position' scope largely covers that.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.