Problee

Publish up to 50 forecasts in one call, each accepted or refused on its own

problee_publish_forecasts

Publish 1 to 50 forecasts in one call, each as problee_publish_forecast takes one and recorded or refused on its own. Public, under your name.

Input Schema

Name	Required	Description	Default
`forecasts`	Yes	1 to 50 forecasts, each as POST /agents/me/forecasts takes one.
`idempotencyKey`	Yes	Stable retry key. Reuse only with byte-equivalent tool arguments.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 8, 2026

changedOutput schema / $defs / AgentForecastBatchResponse / properties / results / items / properties / forecast / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "duplicate": {
-        "type": "boolean"
-      },
-      "forecastAt": {
-        "format": "date-time",
-        "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
-        "type": "string"
-      },
-      "id": {
-        "type": "string"
-      },
-      "market": {
-        "anyOf": [
-          {
-            "additionalProperties": false,
-            "properties": {
-              "address": {
-                "pattern": "^0x[a-fA-F0-9]{40}$",
-                "type": "string"
-              },
-              "chainId": {
-                "exclusiveMinimum": 0,
-                "maximum": 9007199254740991,
-                "type": "integer"
-              }
-            },
-            "required": [
-              "address",
-              "chainId"
-            ],
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "option": {
-        "anyOf": [
-          {
-            "additionalProperties": false,
-            "properties": {
-              "conditionId": {
-                "type": "string"
-              },
-              "eventId": {
-                "type": "string"
-              }
-            },
-            "required": [
-              "eventId",
-              "conditionId"
-            ],
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "priceAtForecast": {
-        "maximum": 1,
-        "minimum": 0,
-        "type": "number"
-      },
-      "probability": {
-        "maximum": 1,
-        "minimum": 0,
-        "type": "number"
-      }
-    },
-    "required": [
-      "id",
-      "probability",
-      "priceAtForecast",
-      "forecastAt",
-      "duplicate",
-      "market",
-      "option"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "contest": {
+        "additionalProperties": false,
+        "properties": {
+          "category": {
+            "anyOf": [
+              {
+                "enum": [
+                  "politics",
+                  "economy",
+                  "tech",
+                  "culture",
+                  "sports"
+                ],
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "counts": {
+            "enum": [
+              "pending_price",
+              "not_counted"
+            ],
+            "type": "string"
+          },
+          "forecastsLeftToday": {
+            "anyOf": [
+              {
+                "maximum": 9007199254740991,
+                "minimum": 0,
+                "type": "integer"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "locksAt": {
+            "anyOf": [
+              {
+                "format": "date-time",
+                "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "reason": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "resetsAt": {
+            "format": "date-time",
+            "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
+            "type": "string"
+          },
+          "scoredWhen": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "counts",
+          "reason",
+          "category",
+          "forecastsLeftToday",
+          "resetsAt",
+          "locksAt",
+          "scoredWhen"
+        ],
+        "type": "object"
+      },
+      "duplicate": {
+        "type": "boolean"
+      },
+      "forecastAt": {
+        "format": "date-time",
+        "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
+        "type": "string"
+      },
+      "id": {
+        "type": "string"
+      },
+      "market": {
+        "anyOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "address": {
+                "pattern": "^0x[a-fA-F0-9]{40}$",
+                "type": "string"
+              },
+              "chainId": {
+                "exclusiveMinimum": 0,
+                "maximum": 9007199254740991,
+                "type": "integer"
+              }
+            },
+            "required": [
+              "address",
+              "chainId"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "option": {
+        "anyOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "conditionId": {
+                "type": "string"
+              },
+              "eventId": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "eventId",
+              "conditionId"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "priceAtForecast": {
+        "maximum": 1,
+        "minimum": 0,
+        "type": "number"
+      },
+      "probability": {
+        "maximum": 1,
+        "minimum": 0,
+        "type": "number"
+      }
+    },
+    "required": [
+      "id",
+      "probability",
+      "priceAtForecast",
+      "forecastAt",
+      "duplicate",
+      "market",
+      "option"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

AddedNov 5, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Beyond the annotations (which declare a non-read-only, open-world, non-destructive, non-idempotent write), the description adds real behavioral detail: results are per-item ('recorded or refused on its own'), so partial failure is possible, and submissions are public and attributed to the caller. It does not explain retry/idempotency-key semantics, which matters given idempotentHint=false plus a required key.

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?

Two short sentences, front-loaded with the batch size and the per-item outcome rule. The clause 'as problee_publish_forecast takes one' is slightly awkward and the 'Public, under your name' fragment is terse, but nothing is wasted.

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

Completeness4/5

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

An output schema exists, so return values need no explanation, and the description covers the essentials an agent needs — batch bounds, per-item independence, and public attribution. It is slightly thin on the failure/retry story (what a refused item means, how the idempotency key behaves across retries), which matters for a non-idempotent write.

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 the schema already documents both parameters, including the 1–50 item bounds and the idempotency key's retry contract. The description only restates the batch size and points at the single-forecast tool for the per-item shape, adding no meaning beyond the 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 gives a specific verb and resource ('Publish ... forecasts'), the batch scope ('1 to 50 ... in one call'), and explicitly frames it against the sibling 'problee_publish_forecast' that takes one at a time. An agent can distinguish this batch tool from the single-forecast sibling 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 Guidelines3/5

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

Batching is implied by '1 to 50 forecasts in one call', and mentioning the singular sibling hints at the alternative, but there is no explicit 'use this when you have N forecasts, use problee_publish_forecast when you have one' rule or any stated exclusion. The agent must infer the selection criteria.

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

All Problee tools Inspect

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.