Bay Run

solve_task

Route and execute one task-shaped call without learning quote/run shapes. Use it when you do not know a pin_id: toxicity, embeddings, and reranking return the compact job answer (labels, vector metadata, ranking) bound by the provenance receipt; guard, sentiment (SST-2 polarity only; sarcasm/irony confidently wrong except one bounded probe cue), support tickets (3 labels + abstain), and lexical rerank reuse the canonical Pins with their decision evidence. Fail-closed: an unbound result escalates. Support-ticket routing/triage requests reuse the existing provisional canonical Pin route_571826c40685073a99510b1951e60338 when the caller omits a taxonomy or supplies exactly access_issue, billing_issue, and delivery_issue; arbitrary caller labels and examples remain caller-defined and are never remapped. Sentiment, polarity, urgency, severity, or unrelated classification remain on their requested path. Urgency, severity, and priority classification must include candidate_labels or labeled examples; Bay Run refuses to invent that taxonomy. Free during launch: no card, no signup, no email. Mint a durable key with POST https://run.huggingbay.xyz/v1/keys/free

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	No	Set to 'quote' for a free compact Pin quote without execution.
`task`	No	Alias for task_description.
`text`	No	Alias for input.
`input`	No	Task input. Send text/list for ordinary tasks or an object with query/documents, content, candidate_labels, or schema. Alias: query, text, content.
`query`	No	Alias for input or structured query.
`content`	No	Alias for input.
`examples`	No	Optional labeled input/expected examples.
`task_hint`	No	Alias for task_description.
`my_examples`	No	Alias for examples.
`min_evidence`	No	Minimum evidence level accepted by an explicit quote.	provisional
`max_price_usd`	No	Quote-only hard price ceiling; Pins above it are rejected before ranking.
`max_latency_ms`	No	Quote-only hard latency ceiling; unmeasured Pins are rejected honestly.
`omit_raw_result`	No	Decision-first projection. Defaults true for MCP: omit the raw model result while retaining decision, route, and receipt evidence.
`task_description`	No	Plain-language task to solve; Bay Run infers the model family. Alias: task, task_hint. Support-ticket routing/triage requests reuse the existing provisional canonical Pin route_571826c40685073a99510b1951e60338 when the caller omits a taxonomy or supplies exactly access_issue, billing_issue, and delivery_issue; arbitrary caller labels and examples remain caller-defined and are never remapped. Sentiment, polarity, urgency, severity, or unrelated classification remain on their requested path. Urgency, severity, and priority classification must include candidate_labels or labeled examples; Bay Run refuses to invent that taxonomy.
`external_apis_allowed`	No	Allow Pins whose data policy permits external APIs.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`route`	No
`answer`	No
`result`	No
`schema`	No
`receipt`	No
`results`	No
`decision`	No
`quote_id`	No
`rejected`	No
`next_call`	No
`charged_usd`	No
`routed_model`	No
`receipt_status`	No
`decision_evidence`	No
`raw_result_omitted`	No
`task_kind_inference`	No
`cheapest_capable_pin_id`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedSep 2, 2026

changedOutput schema / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "description": "MCP output schema accepting legacy decisions and compact Pin quotes.",
-    "properties": {
-      "decision": {
-        "anyOf": [
-          {
-            "additionalProperties": true,
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Decision"
-      },
-      "decision_evidence": {
-        "anyOf": [
-          {
-            "additionalProperties": true,
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Decision Evidence"
-      },
-      "next_call": {
-        "additionalProperties": true,
-        "title": "Next Call",
-        "type": "object"
-      },
-      "raw_result_omitted": {
-        "anyOf": [
-          {
-            "const": true,
-            "type": "boolean"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Raw Result Omitted"
-      },
-      "receipt": {
-        "anyOf": [
-          {
-            "additionalProperties": true,
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Receipt"
-      },
-      "receipt_status": {
-        "title": "Receipt Status",
-        "type": "string"
-      },
-      "result": {
-        "default": null,
-        "title": "Result"
-      },
-      "route": {
-        "additionalProperties": true,
-        "title": "Route",
-        "type": "object"
-      },
-      "routed_model": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Routed Model"
-      },
-      "schema": {
-        "title": "Schema",
-        "type": "string"
-      },
-      "task_kind_inference": {
-        "anyOf": [
-          {
-            "additionalProperties": true,
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Task Kind Inference"
-      }
-    },
-    "required": [
-      "schema",
-      "receipt_status",
-      "route",
-      "next_call"
-    ],
-    "title": "SolveTaskMCPResponse",
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "description": "The receipt-free response contract for an explicit Pin quote.",
-    "properties": {
-      "charged_usd": {
-        "title": "Charged Usd",
-        "type": "number"
-      },
-      "cheapest_capable_pin_id": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Cheapest Capable Pin Id"
-      },
-      "quote_id": {
-        "title": "Quote Id",
-        "type": "string"
-      },
-      "rejected": {
-        "items": {
-          "additionalProperties": true,
-          "type": "object"
-        },
-        "title": "Rejected",
-        "type": "array"
-      },
-      "results": {
-        "items": {
-          "additionalProperties": true,
-          "type": "object"
-        },
-        "title": "Results",
-        "type": "array"
-      },
-      "schema": {
-        "const": "bay-run.pin-quote.v1",
-        "title": "Schema",
-        "type": "string"
-      }
-    },
-    "required": [
-      "schema",
-      "results",
-      "rejected",
-      "quote_id",
-      "charged_usd"
-    ],
-    "title": "CompactPinQuoteResponse",
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "description": "MCP output schema accepting legacy decisions and compact Pin quotes.",
+    "properties": {
+      "answer": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Answer"
+      },
+      "decision": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Decision"
+      },
+      "decision_evidence": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Decision Evidence"
+      },
+      "next_call": {
+        "additionalProperties": true,
+        "title": "Next Call",
+        "type": "object"
+      },
+      "raw_result_omitted": {
+        "anyOf": [
+          {
+            "const": true,
+            "type": "boolean"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Raw Result Omitted"
+      },
+      "receipt": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Receipt"
+      },
+      "receipt_status": {
+        "title": "Receipt Status",
+        "type": "string"
+      },
+      "result": {
+        "default": null,
+        "title": "Result"
+      },
+      "route": {
+        "additionalProperties": true,
+        "title": "Route",
+        "type": "object"
+      },
+      "routed_model": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Routed Model"
+      },
+      "schema": {
+        "title": "Schema",
+        "type": "string"
+      },
+      "task_kind_inference": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Task Kind Inference"
+      }
+    },
+    "required": [
+      "schema",
+      "receipt_status",
+      "route",
+      "next_call"
+    ],
+    "title": "SolveTaskMCPResponse",
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "description": "The receipt-free response contract for an explicit Pin quote.",
+    "properties": {
+      "charged_usd": {
+        "title": "Charged Usd",
+        "type": "number"
+      },
+      "cheapest_capable_pin_id": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Cheapest Capable Pin Id"
+      },
+      "quote_id": {
+        "title": "Quote Id",
+        "type": "string"
+      },
+      "rejected": {
+        "items": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "title": "Rejected",
+        "type": "array"
+      },
+      "results": {
+        "items": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "title": "Results",
+        "type": "array"
+      },
+      "schema": {
+        "const": "bay-run.pin-quote.v1",
+        "title": "Schema",
+        "type": "string"
+      }
+    },
+    "required": [
+      "schema",
+      "results",
+      "rejected",
+      "quote_id",
+      "charged_usd"
+    ],
+    "title": "CompactPinQuoteResponse",
+    "type": "object"
+  }
+]

addedOutput schema / properties / answer

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Answer"
+}

Changed15 schema fields changedSep 1, 2026

addedInput schema / properties / external_apis_allowed

Added value: +{
+  "default": false,
+  "description": "Allow Pins whose data policy permits external APIs.",
+  "title": "External Apis Allowed",
+  "type": "boolean"
+}

addedInput schema / properties / max_latency_ms

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 300000,
+      "minimum": 1,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Quote-only hard latency ceiling; unmeasured Pins are rejected honestly.",
+  "title": "Max Latency Ms"
+}

addedInput schema / properties / max_price_usd

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Quote-only hard price ceiling; Pins above it are rejected before ranking.",
+  "title": "Max Price Usd"
+}

addedInput schema / properties / min_evidence

Added value: +{
+  "default": "provisional",
+  "description": "Minimum evidence level accepted by an explicit quote.",
+  "title": "Min Evidence",
+  "type": "string"
+}

addedInput schema / properties / mode

Added value: +{
+  "anyOf": [
+    {
+      "const": "quote",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Set to 'quote' for a free compact Pin quote without execution.",
+  "title": "Mode"
+}

removedOutput schema / additionalProperties
```
Removed value: -false
```

addedOutput schema / anyOf

Added value: +[
+  {
+    "additionalProperties": false,
+    "description": "MCP output schema accepting legacy decisions and compact Pin quotes.",
+    "properties": {
+      "decision": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Decision"
+      },
+      "decision_evidence": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Decision Evidence"
+      },
+      "next_call": {
+        "additionalProperties": true,
+        "title": "Next Call",
+        "type": "object"
+      },
+      "raw_result_omitted": {
+        "anyOf": [
+          {
+            "const": true,
+            "type": "boolean"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Raw Result Omitted"
+      },
+      "receipt": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Receipt"
+      },
+      "receipt_status": {
+        "title": "Receipt Status",
+        "type": "string"
+      },
+      "result": {
+        "default": null,
+        "title": "Result"
+      },
+      "route": {
+        "additionalProperties": true,
+        "title": "Route",
+        "type": "object"
+      },
+      "routed_model": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Routed Model"
+      },
+      "schema": {
+        "title": "Schema",
+        "type": "string"
+      },
+      "task_kind_inference": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Task Kind Inference"
+      }
+    },
+    "required": [
+      "schema",
+      "receipt_status",
+      "route",
+      "next_call"
+    ],
+    "title": "SolveTaskMCPResponse",
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "description": "The receipt-free response contract for an explicit Pin quote.",
+    "properties": {
+      "charged_usd": {
+        "title": "Charged Usd",
+        "type": "number"
+      },
+      "cheapest_capable_pin_id": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Cheapest Capable Pin Id"
+      },
+      "quote_id": {
+        "title": "Quote Id",
+        "type": "string"
+      },
+      "rejected": {
+        "items": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "title": "Rejected",
+        "type": "array"
+      },
+      "results": {
+        "items": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "title": "Results",
+        "type": "array"
+      },
+      "schema": {
+        "const": "bay-run.pin-quote.v1",
+        "title": "Schema",
+        "type": "string"
+      }
+    },
+    "required": [
+      "schema",
+      "results",
+      "rejected",
+      "quote_id",
+      "charged_usd"
+    ],
+    "title": "CompactPinQuoteResponse",
+    "type": "object"
+  }
+]

changedOutput schema / description

Previous value: -"Explicit MCP/REST output contract for the one-call task meta-tool."New value: +"MCP output schema accepting legacy decisions and compact Pin quotes."

addedOutput schema / properties / charged_usd

Added value: +{
+  "title": "Charged Usd",
+  "type": "number"
+}

addedOutput schema / properties / cheapest_capable_pin_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Cheapest Capable Pin Id"
+}

addedOutput schema / properties / quote_id

Added value: +{
+  "title": "Quote Id",
+  "type": "string"
+}

addedOutput schema / properties / rejected

Added value: +{
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "title": "Rejected",
+  "type": "array"
+}

addedOutput schema / properties / results

Added value: +{
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "title": "Results",
+  "type": "array"
+}

removedOutput schema / required

Removed value: -[
-  "schema",
-  "receipt_status",
-  "route",
-  "next_call"
-]

changedOutput schema / title

Previous value: -"SolveTaskResponse"New value: +"SolveTaskMCPResponse"

Changed5 schema fields changedAug 31, 2026

removedOutput schema / properties / task_kind_inference / additionalProperties
```
Removed value: -true
```

addedOutput schema / properties / task_kind_inference / anyOf

Added value: +[
+  {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

addedOutput schema / properties / task_kind_inference / default
```
Added value: +null
```
removedOutput schema / properties / task_kind_inference / type
```
Removed value: -"object"
```

changedOutput schema / required

Previous value: -[
-  "schema",
-  "receipt_status",
-  "task_kind_inference",
-  "route",
-  "next_call"
-]New value: +[
+  "schema",
+  "receipt_status",
+  "route",
+  "next_call"
+]

Changed1 schema field changedAug 27, 2026

addedOutput schema / properties / decision_evidence

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Decision Evidence"
+}

Changed4 schema fields changedAug 26, 2026

addedInput schema / properties / omit_raw_result

Added value: +{
+  "default": true,
+  "description": "Decision-first projection. Defaults true for MCP: omit the raw model result while retaining decision, route, and receipt evidence.",
+  "title": "Omit Raw Result",
+  "type": "boolean"
+}

addedOutput schema / properties / raw_result_omitted

Added value: +{
+  "anyOf": [
+    {
+      "const": true,
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Raw Result Omitted"
+}

addedOutput schema / properties / result / default
```
Added value: +null
```

changedOutput schema / required

Previous value: -[
-  "schema",
-  "result",
-  "receipt_status",
-  "task_kind_inference",
-  "route",
-  "next_call"
-]New value: +[
+  "schema",
+  "receipt_status",
+  "task_kind_inference",
+  "route",
+  "next_call"
+]

Changed2 schema fields changedAug 26, 2026

changedInput schema / properties / task_description / description

Previous value: -"Plain-language task to solve; Bay Run infers the model family. Alias: task, task_hint. Support-ticket routing/triage requests with no caller-supplied candidate_labels or labeled examples reuse the existing provisional canonical Pin route_571826c40685073a99510b1951e60338; explicit labels/examples and sentiment, polarity, urgency, severity, or unrelated classification remain on their requested path. Urgency, severity, and priority classification must include candidate_labels or labeled examples; Bay Run refuses to invent that taxonomy."New value: +"Plain-language task to solve; Bay Run infers the model family. Alias: task, task_hint. Support-ticket routing/triage requests reuse the existing provisional canonical Pin route_571826c40685073a99510b1951e60338 when the caller omits a taxonomy or supplies exactly access_issue, billing_issue, and delivery_issue; arbitrary caller labels and examples remain caller-defined and are never remapped. Sentiment, polarity, urgency, severity, or unrelated classification remain on their requested path. Urgency, severity, and priority classification must include candidate_labels or labeled examples; Bay Run refuses to invent that taxonomy."

addedOutput schema / properties / decision

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Decision"
+}

Changed1 schema field changedAug 26, 2026

changedInput schema / properties / task_description / description

Previous value: -"Plain-language task to solve; Bay Run infers the model family. Alias: task, task_hint. Support-ticket routing/triage requests with no caller-supplied candidate_labels or labeled examples reuse the existing provisional canonical Pin route_571826c40685073a99510b1951e60338; explicit labels/examples and sentiment, polarity, urgency, or unrelated classification remain on their requested path."New value: +"Plain-language task to solve; Bay Run infers the model family. Alias: task, task_hint. Support-ticket routing/triage requests with no caller-supplied candidate_labels or labeled examples reuse the existing provisional canonical Pin route_571826c40685073a99510b1951e60338; explicit labels/examples and sentiment, polarity, urgency, severity, or unrelated classification remain on their requested path. Urgency, severity, and priority classification must include candidate_labels or labeled examples; Bay Run refuses to invent that taxonomy."

Changed1 schema field changedAug 23, 2026

changedInput schema / properties / task_description / description

Previous value: -"Plain-language task to solve; Bay Run infers the model family. Alias: task, task_hint."New value: +"Plain-language task to solve; Bay Run infers the model family. Alias: task, task_hint. Support-ticket routing/triage requests with no caller-supplied candidate_labels or labeled examples reuse the existing provisional canonical Pin route_571826c40685073a99510b1951e60338; explicit labels/examples and sentiment, polarity, urgency, or unrelated classification remain on their requested path."

Changed7 schema fields changedAug 21, 2026

addedInput schema / properties / input / default
```
Added value: +null
```

changedInput schema / properties / input / description

Previous value: -"Task input. Send text/list for ordinary tasks or an object with query/documents, content, candidate_labels, or schema."New value: +"Task input. Send text/list for ordinary tasks or an object with query/documents, content, candidate_labels, or schema. Alias: query, text, content."

addedInput schema / properties / task_description / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / task_description / default
```
Added value: +null
```

changedInput schema / properties / task_description / description

Previous value: -"Plain-language task to solve; Bay Run infers the model family."New value: +"Plain-language task to solve; Bay Run infers the model family. Alias: task, task_hint."

removedInput schema / properties / task_description / type
```
Removed value: -"string"
```

removedInput schema / required

Removed value: -[
-  "task_description",
-  "input"
-]

Changed9 schema fields changedAug 20, 2026

addedInput schema / properties / content

Added value: +{
+  "anyOf": [
+    {},
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Alias for input.",
+  "title": "Content"
+}

addedInput schema / properties / examples

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional labeled input/expected examples.",
+  "title": "Examples"
+}

addedInput schema / properties / my_examples

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Alias for examples.",
+  "title": "My Examples"
+}

addedInput schema / properties / query

Added value: +{
+  "anyOf": [
+    {},
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Alias for input or structured query.",
+  "title": "Query"
+}

addedInput schema / properties / task

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Alias for task_description.",
+  "title": "Task"
+}

removedInput schema / properties / task_description / maxLength
```
Removed value: -1000
```
removedInput schema / properties / task_description / minLength
```
Removed value: -3
```

addedInput schema / properties / task_hint

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Alias for task_description.",
+  "title": "Task Hint"
+}

addedInput schema / properties / text

Added value: +{
+  "anyOf": [
+    {},
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Alias for input.",
+  "title": "Text"
+}

Changed2 schema fields changedAug 18, 2026

addedOutput schema / properties / task_kind_inference

Added value: +{
+  "additionalProperties": true,
+  "title": "Task Kind Inference",
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "schema",
-  "result",
-  "receipt_status",
-  "route",
-  "next_call"
-]New value: +[
+  "schema",
+  "result",
+  "receipt_status",
+  "task_kind_inference",
+  "route",
+  "next_call"
+]

AddedAug 18, 2026

TDQS

A4.4/5.0

Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so thoroughly: fail-closed escalation on unbound results, known sentiment failure modes, canonical route reuse, refusal to remap caller labels, and free key minting instructions are all disclosed. This goes well beyond the schema.

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 description is dense and long, but it front-loads the main purpose and use condition. Caveats are packed into one paragraph, so it loses a point for lack of structural separation, though most sentences earn their place given the tool's complexity.

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 complex 15-parameter tool with no annotations, the description covers routing paths, failure behavior, taxonomy constraints, authentication, and cost-related caveats. With an output schema present, it does not need to describe return values, and nothing critical to correct invocation appears missing.

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 all 15 parameters. The description adds useful routing context for task_description and input, but it does not substantially enrich individual parameter semantics beyond what the schema already provides.

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 opens with a specific verb and resource: 'Route and execute one task-shaped call', and immediately adds the key selector 'when you do not know a pin_id'. This clearly distinguishes solve_task from pin-id-based tools and gives an agent a concrete job-to-do.

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 explicitly states when to use the tool: when a pin_id is unknown, and it gives routing rules for support tickets, sentiment, toxicity, and reranking. It also provides negative constraints such as refusing to invent urgency/severity taxonomies, though it does not name sibling tools like run_pin or coprocessor as alternatives.

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

All Bay Run 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

A4.1/5.0

Disambiguation4/5

coprocessor is clearly distinct as a guard-before-action tool, while run_pin and solve_task both execute tasks and are differentiated mainly by whether a pin_id is known. The descriptions are verbose but do enough to separate the intent.

Naming Consistency2/5

run_pin and solve_task follow a verb_noun snake_case pattern, but coprocessor is a single noun with no verb, breaking the convention. The mix of noun-style and verb-style names creates inconsistency.

Tool Count4/5

Three tools is on the lean side but appropriate for an execution-focused server spanning guard, known-pin execution, and task routing without a pin_id. Each tool covers a distinct operation, though the extremely verbose descriptions make the set feel denser than the count suggests.

Completeness4/5

The core lifecycle of guarding, running a known pin, and routing an unknown task is covered. Minor gaps exist such as no tool for listing or inspecting pins, but the server's stated purpose is execution rather than pin management, so the coverage is mostly sufficient.

solve_task

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources