Skip to main content
Glama
longbridge

longbridge

Official
by longbridge
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
Rust
Hybrid

Security Facts

security_facts
Read-onlyIdempotent

Retrieve catalyst events, anomaly detections, and factor readings for a symbol within a time range to identify the triggers that strategy signals reference.

Instructions

List a security's fact (catalyst) events — anomaly detections, factor readings, data sources and natural-language summaries — filtered by time range and count. Facts are what strategies react to: a signal names its trigger in key_fact_id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
_jqNoOptional jq filter (jaq syntax) applied to this tool's JSON response before it is returned; it never changes the upstream request. One output is returned as-is, several as a JSON array, none as []. Module imports and the `env`/`debug`/`stderr` builtins are unavailable. Example: .data | map({symbol}). Omit for the full response.
limitNoThe maximum number of facts to return. If the number of facts in the time range exceeds this limit, only the latest 'limit' facts will be returned. Defaults to 100.
symbolYesSecurity symbol to query, e.g. "AAPL.US" or "700.HK".
end_timeNoThe end time of the fact to be queried, formatted as 2006-01-02T15:04:05Z in UTC Timezone. If left empty, the query will default to retrieving the latest data.
begin_timeNoThe optional start time of the fact query, formatted as 2006-01-02T15:04:05Z in UTC Timezone. If left empty, the query will include the earliest available data.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.12.0
    • addedInput schema / properties / _jq / description
      Added value: +"Optional jq filter (jaq syntax) applied to this tool's JSON response before it is returned; it never changes the upstream request. One output is returned as-is, several as a JSON array, none as []. Module imports and the `env`/`debug`/`stderr` builtins are unavailable. Example: .data | map({symbol}). Omit for the full response."
    • removedInput schema / properties / limit / format
      Removed value: -"int32"
  2. Changed2 schema fields changedv0.10.6
    • addedInput schema / properties / _jq
      Added value: +{
+  "type": "string"
+}
    • changedOutput schema / (root)
      Previous value: -{
-  "$defs": {
-    "AnomalyDetection": {
-      "properties": {
-        "anomaly_result": {
-          "type": "string"
-        },
-        "significance_level": {
-          "type": "string"
-        },
-        "test_method": {
-          "type": "string"
-        },
-        "thresholds": {
-          "$ref": "#/$defs/AnomalyThresholds"
-        }
-      },
-      "required": [
-        "anomaly_result",
-        "significance_level",
-        "test_method",
-        "thresholds"
-      ],
-      "type": "object"
-    },
-    "AnomalyThresholds": {
-      "properties": {
-        "high": {
-          "type": "string"
-        },
-        "low": {
-          "type": "string"
-        },
-        "medium": {
-          "type": "string"
-        }
-      },
-      "required": [
-        "low",
-        "medium",
-        "high"
-      ],
-      "type": "object"
-    },
-    "FactDataSource": {
-      "properties": {
-        "icon": {
-          "type": "string"
-        },
-        "source_name": {
-          "type": "string"
-        },
-        "type": {
-          "$ref": "#/$defs/FactType"
-        },
-        "url": {
-          "type": "string"
-        }
-      },
-      "required": [
-        "source_name",
-        "type",
-        "url",
-        "icon"
-      ],
-      "type": "object"
-    },
-    "FactDirection": {
-      "enum": [
-        "long",
-        "short",
-        "neutral",
-        ""
-      ],
-      "type": "string"
-    },
-    "FactFactor": {
-      "properties": {
-        "anomaly_detection": {
-          "$ref": "#/$defs/AnomalyDetection"
-        },
-        "factor_groups": {
-          "items": {
-            "type": "string"
-          },
-          "type": "array"
-        },
-        "long_short_direction": {
-          "$ref": "#/$defs/FactDirection"
-        },
-        "name": {
-          "type": "string"
-        },
-        "trigger_condition": {
-          "type": "string"
-        }
-      },
-      "required": [
-        "name",
-        "factor_groups",
-        "long_short_direction",
-        "trigger_condition",
-        "anomaly_detection"
-      ],
-      "type": "object"
-    },
-    "FactNlInfo": {
-      "properties": {
-        "eli_explain": {
-          "$ref": "#/$defs/NlField"
-        },
-        "invest_anal": {
-          "$ref": "#/$defs/NlField"
-        },
-        "sub_title": {
-          "type": "string"
-        },
-        "summary": {
-          "$ref": "#/$defs/NlField"
-        },
-        "title": {
-          "type": "string"
-        }
-      },
-      "required": [
-        "title",
-        "sub_title",
-        "summary",
-        "invest_anal",
-        "eli_explain"
-      ],
-      "type": "object"
-    },
-    "FactSymbol": {
-      "properties": {
-        "security_name": {
-          "type": "string"
-        },
-        "symbol": {
-          "type": "string"
-        }
-      },
-      "required": [
-        "symbol",
-        "security_name"
-      ],
-      "type": "object"
-    },
-    "FactType": {
-      "enum": [
-        "News",
-        "Fundamental",
-        "Technical",
-        "Unknown"
-      ],
-      "type": "string"
-    },
-    "NlField": {
-      "anyOf": [
-        {
-          "items": {
-            "$ref": "#/$defs/NlTag"
-          },
-          "type": "array"
-        },
-        {
-          "type": "string"
-        }
-      ]
-    },
-    "NlTag": {
-      "properties": {
-        "tag": {
-          "type": "string"
-        },
-        "value": {
-          "type": "string"
-        }
-      },
-      "required": [
-        "tag",
-        "value"
-      ],
-      "type": "object"
-    },
-    "SecurityFactItem": {
-      "properties": {
-        "data_source": {
-          "items": {
-            "$ref": "#/$defs/FactDataSource"
-          },
-          "type": "array"
-        },
-        "direction": {
-          "$ref": "#/$defs/FactDirection"
-        },
-        "fact_id": {
-          "type": "string"
-        },
-        "fact_type": {
-          "$ref": "#/$defs/FactType"
-        },
-        "factors": {
-          "items": {
-            "$ref": "#/$defs/FactFactor"
-          },
-          "type": "array"
-        },
-        "nl_info": {
-          "$ref": "#/$defs/FactNlInfo"
-        },
-        "occur_time": {
-          "type": "string"
-        },
-        "symbols_info": {
-          "items": {
-            "$ref": "#/$defs/FactSymbol"
-          },
-          "type": "array"
-        }
-      },
-      "required": [
-        "fact_id",
-        "fact_type",
-        "direction",
-        "occur_time",
-        "symbols_info",
-        "factors",
-        "data_source",
-        "nl_info"
-      ],
-      "type": "object"
-    }
-  },
-  "properties": {
-    "facts": {
-      "items": {
-        "$ref": "#/$defs/SecurityFactItem"
-      },
-      "type": "array"
-    }
-  },
-  "required": [
-    "facts"
-  ],
-  "type": "object"
-}New value: +null
  3. Addedv0.10.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish the tool as read-only, idempotent, and non-destructive, lowering the burden on the description. The description adds value by specifying the nature of the returned data (catalyst events, including anomaly detections and summaries) and the key_fact_id linkage, which helps the agent understand the content and purpose beyond the safety profile.

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?

Two sentences with zero filler. The first sentence delivers the core action, scope, and filters; the second adds the conceptual framing (facts as triggers). The most important information is front-loaded, making it easy to scan.

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?

For a tool with no output schema and five parameters, the description covers the essential aspects: what is listed, event types, filtering capabilities, and the relationship to signals. It does not describe the exact response shape or pagination, but the schema explains defaults and the description gives enough context for an agent to make a reasonable first call. Minor gap given no output schema, but overall adequate.

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%, with each parameter having detailed descriptions (e.g., time formats, limit default, symbol format). The description reinforces that begin_time/end_time/limit control filtering and count, but it adds no new parameter-specific meaning beyond what the schema already provides. Baseline of 3 is appropriate.

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 clearly states the tool lists a security's fact (catalyst) events, enumerates specific event types (anomaly detections, factor readings, data sources, natural-language summaries), and mentions filtering by time range and count. It distinguishes itself from related siblings like anomaly and signals by framing facts as the triggers that signals reference, making its purpose unambiguous.

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?

The description provides contextual guidance: 'Facts are what strategies react to' and 'a signal names its trigger in key_fact_id,' which implies when to use this tool (to inspect the underlying causes behind signals). However, it does not explicitly contrast with alternatives like anomaly, signals, or signal_detail, nor does it state when not to use it, so it falls short of the top tier.

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

Deploy Server

Other Tools