Skip to main content
Glama

Candor Finance

by money.candor
OverviewDiscussionsAdmin

Inspect Candor changes

candor_changes

Returns computed comparisons for spending, income, recurring payments, account terms, and investment positions, with basis handles and coverage caveats. Use when the user asks how spending, income, recurring payments, account terms, or holdings changed between periods. Spending and income compare recorded posted totals across inclusive since/until and comparison_since/comparison_until ranges; without ranges, the last complete UTC calendar month is compared with the month before, and the response states both ranges. limit trims the items returned without changing the comparison. When source history is incomplete or evidence is capped, spending and income comparisons are withheld. The read is recorded with its reason and does not change the opening checkpoint, seen activity, attention items, or due notes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum change items to return, from 1 to 1000; defaults to 25. Only trims output, never the comparison evidence.
sinceNoInclusive start of the current range (YYYY-MM-DD). Supply all four range dates for spending or income comparisons.
untilNoInclusive end of the current range (YYYY-MM-DD).
domainNoRestrict to one change domain; omitted or all includes every supported domain. Values: all, spending, income, recurring, account_terms, investments.
reasonNoConcise user-visible purpose recorded in immutable action history, including for financial reads. It names the task, such as "Check this month's dining budget", and needs no personal details from the conversation. A reason is not approval. Root operations require it except fixed-reason orientation operations; continuations inherit the parent reason only when no reason is supplied. Fixed-reason orientation operations always use their system reason.
task_keyNoOptional stable label grouping operations for the same user task. Omit to inherit the parent task key, if any. It does not schedule work or provide idempotency.
parent_actionNoExisting action id in this workspace, typically returned in next_actions, that this continuation follows. A continuation with the parent's reason joins the parent's root action, whether the reason is omitted (it is then inherited) or repeated exactly; a distinct explicit reason is preserved and starts a new root that keeps this parent link. Fixed-reason orientation operations always start a new root. Omit for a new root action.
comparison_sinceNoInclusive start of the comparison range (YYYY-MM-DD).
comparison_untilNoInclusive end of the comparison range (YYYY-MM-DD).
account_identity_idNoRestrict changes to one durable account identity before applying history caps. This scope applies to every domain; for investments it reads that account's own position observations, so a busy vault cannot crowd the account out of the capped read.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataYes
actionNo
errorsYes
statusYes
metadataNo
warningsYes
request_idYes
generated_atYes
next_actionsYes
user_messageNo
data_freshnessNo
schema_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / parent_action / description
      Previous value: -"Existing action id in this workspace, typically returned in next_actions, whose root identity this continuation inherits. An omitted reason inherits the parent reason; an explicit reason is preserved, except for fixed-reason orientation operations. Omit for a new root action."New value: +"Existing action id in this workspace, typically returned in next_actions, that this continuation follows. A continuation with the parent's reason joins the parent's root action, whether the reason is omitted (it is then inherited) or repeated exactly; a distinct explicit reason is preserved and starts a new root that keeps this parent link. Fixed-reason orientation operations always start a new root. Omit for a new root action."
  2. Changed1 schema field changed
    • changedInput schema / properties / reason / description
      Previous value: -"Concise user-visible purpose recorded in immutable action history, including for financial reads. A reason is not approval. Root operations require it except fixed-reason orientation operations; continuations inherit the parent reason only when no reason is supplied. Fixed-reason orientation operations always use their system reason."New value: +"Concise user-visible purpose recorded in immutable action history, including for financial reads. It names the task, such as \"Check this month's dining budget\", and needs no personal details from the conversation. A reason is not approval. Root operations require it except fixed-reason orientation operations; continuations inherit the parent reason only when no reason is supplied. Fixed-reason orientation operations always use their system reason."
  3. Changed12 schema fields changed
    • addedInput schema / properties / account_identity_id / description
      Added value: +"Restrict changes to one durable account identity before applying history caps. This scope applies to every domain; for investments it reads that account's own position observations, so a busy vault cannot crowd the account out of the capped read."
    • addedInput schema / properties / comparison_since
      Added value: +{
+  "description": "Inclusive start of the comparison range (YYYY-MM-DD).",
+  "type": "string"
+}
    • addedInput schema / properties / comparison_until
      Added value: +{
+  "description": "Inclusive end of the comparison range (YYYY-MM-DD).",
+  "type": "string"
+}
    • addedInput schema / properties / domain / description
      Added value: +"Restrict to one change domain; omitted or all includes every supported domain. Values: all, spending, income, recurring, account_terms, investments."
    • removedInput schema / properties / inline_response
      Removed value: -{
-  "description": "Return the full response payload in this MCP tool result instead of a resource link. Use only when the client can materialize large tool results into a code sandbox; the response may be very large.",
-  "type": "boolean"
-}
    • addedInput schema / properties / limit / description
      Added value: +"Maximum change items to return, from 1 to 1000; defaults to 25. Only trims output, never the comparison evidence."
    • addedInput schema / properties / parent_action / description
      Added value: +"Existing action id in this workspace, typically returned in next_actions, whose root identity this continuation inherits. An omitted reason inherits the parent reason; an explicit reason is preserved, except for fixed-reason orientation operations. Omit for a new root action."
    • changedInput schema / properties / reason / description
      Previous value: -"Concise user-visible reason recorded in action history."New value: +"Concise user-visible purpose recorded in immutable action history, including for financial reads. A reason is not approval. Root operations require it except fixed-reason orientation operations; continuations inherit the parent reason only when no reason is supplied. Fixed-reason orientation operations always use their system reason."
    • addedInput schema / properties / since
      Added value: +{
+  "description": "Inclusive start of the current range (YYYY-MM-DD). Supply all four range dates for spending or income comparisons.",
+  "type": "string"
+}
    • addedInput schema / properties / task_key / description
      Added value: +"Optional stable label grouping operations for the same user task. Omit to inherit the parent task key, if any. It does not schedule work or provide idempotency."
    • addedInput schema / properties / until
      Added value: +{
+  "description": "Inclusive end of the current range (YYYY-MM-DD).",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "reason"
-]
  4. Changed3 schema fields changed
    • changedInput schema / properties / limit / maximum
      Previous value: -100New value: +1000
    • addedOutput schema / properties / metadata / properties
      Added value: +{
+  "view_url": {
+    "format": "uri",
+    "type": "string"
+  }
+}
    • removedOutput schema / properties / metadata / propertyNames
      Removed value: -{
-  "type": "string"
-}
  5. Changed1 schema field changed
    • addedOutput schema / properties / metadata
      Added value: +{
+  "additionalProperties": {},
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}
  6. Changed2 schema fields changed
    • removedOutput schema / properties / summary
      Removed value: -{
-  "minLength": 1,
-  "type": "string"
-}
    • changedOutput schema / required
      Previous value: -[
-  "data",
-  "errors",
-  "generated_at",
-  "next_actions",
-  "request_id",
-  "schema_version",
-  "status",
-  "summary",
-  "warnings"
-]New value: +[
+  "data",
+  "errors",
+  "generated_at",
+  "next_actions",
+  "request_id",
+  "schema_version",
+  "status",
+  "warnings"
+]
  7. Changed2 schema fields changed
    • removedOutput schema / $defs / __schema1
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "number"
-    },
-    {
-      "type": "boolean"
-    },
-    {
-      "type": "null"
-    },
-    {
-      "items": {
-        "$ref": "#/$defs/__schema1"
-      },
-      "type": "array"
-    },
-    {
-      "additionalProperties": {
-        "$ref": "#/$defs/__schema1"
-      },
-      "propertyNames": {
-        "type": "string"
-      },
-      "type": "object"
-    }
-  ]
-}
    • removedOutput schema / properties / query_scope
      Removed value: -{
-  "additionalProperties": false,
-  "properties": {
-    "population": {
-      "additionalProperties": false,
-      "properties": {
-        "included_count": {
-          "maximum": 9007199254740991,
-          "minimum": 0,
-          "type": "integer"
-        },
-        "total_available_count": {
-          "anyOf": [
-            {
-              "maximum": 9007199254740991,
-              "minimum": 0,
-              "type": "integer"
-            },
-            {
-              "type": "null"
-            }
-          ]
-        }
-      },
-      "required": [
-        "included_count",
-        "total_available_count"
-      ],
-      "type": "object"
-    },
-    "query": {
-      "additionalProperties": false,
-      "properties": {
-        "args": {
-          "additionalProperties": {
-            "$ref": "#/$defs/__schema1"
-          },
-          "propertyNames": {
-            "type": "string"
-          },
-          "type": "object"
-        },
-        "operation": {
-          "minLength": 1,
-          "type": "string"
-        }
-      },
-      "required": [
-        "args",
-        "operation"
-      ],
-      "type": "object"
-    }
-  },
-  "required": [
-    "population",
-    "query"
-  ],
-  "type": "object"
-}
  8. Changed2 schema fields changed
    • addedOutput schema / $defs / __schema1
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    },
+    {
+      "items": {
+        "$ref": "#/$defs/__schema1"
+      },
+      "type": "array"
+    },
+    {
+      "additionalProperties": {
+        "$ref": "#/$defs/__schema1"
+      },
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    }
+  ]
+}
    • addedOutput schema / properties / query_scope
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "population": {
+      "additionalProperties": false,
+      "properties": {
+        "included_count": {
+          "maximum": 9007199254740991,
+          "minimum": 0,
+          "type": "integer"
+        },
+        "total_available_count": {
+          "anyOf": [
+            {
+              "maximum": 9007199254740991,
+              "minimum": 0,
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "required": [
+        "included_count",
+        "total_available_count"
+      ],
+      "type": "object"
+    },
+    "query": {
+      "additionalProperties": false,
+      "properties": {
+        "args": {
+          "additionalProperties": {
+            "$ref": "#/$defs/__schema1"
+          },
+          "propertyNames": {
+            "type": "string"
+          },
+          "type": "object"
+        },
+        "operation": {
+          "minLength": 1,
+          "type": "string"
+        }
+      },
+      "required": [
+        "args",
+        "operation"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "population",
+    "query"
+  ],
+  "type": "object"
+}
  9. Changed2 schema fields changed
    • addedOutput schema / $defs
      Added value: +{
+  "__schema0": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "number"
+      },
+      {
+        "type": "boolean"
+      },
+      {
+        "type": "null"
+      },
+      {
+        "items": {
+          "$ref": "#/$defs/__schema0"
+        },
+        "type": "array"
+      },
+      {
+        "additionalProperties": {
+          "$ref": "#/$defs/__schema0"
+        },
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      }
+    ]
+  }
+}
    • addedOutput schema / properties / next_actions / items / properties / args / additionalProperties / $ref
      Added value: +"#/$defs/__schema0"
  10. First observed

TDQS

A4/5.0
Behavior4/5

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

With annotations present the bar is lower, but the description still adds real behavioral context beyond them: the read is recorded with its reason and leaves the opening checkpoint, seen activity, attention items, and due notes untouched, and spending/income comparisons are withheld when history is incomplete. It does not cover authorization requirements or error behavior.

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?

Purpose and trigger are front-loaded before the range and withholding details, and the sentences are dense with distinct facts rather than filler. It runs long, but each sentence adds a separate behavioral or usage fact, so little 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?

For a 10-parameter computed-comparison tool with an output schema, the description covers the trigger, the default window, the withholding condition, and the audit side effect. Return-value detail is correctly left to the output schema; only authorization/error expectations are absent.

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, but the description genuinely extends the schema by specifying the default comparison window (last complete UTC calendar month versus the month before, with both ranges stated in the response) and that all four range dates are required for spending/income comparisons. These are semantics the schema fields alone do not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

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 set: computed comparisons for spending, income, recurring payments, account terms, and investment positions. That is enough for an agent to know what the tool produces, though it never explicitly names or distinguishes the sibling tools (candor_query, candor_get, candor_snapshot) that might compete for the same request.

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 states a clear triggering condition: use when the user asks how spending, income, recurring payments, account terms, or holdings changed between periods. It also documents a when-not/limitation (comparisons withheld when source history is incomplete or evidence is capped). Alternatives are not named, so it stops short of explicit routing.

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

All Candor Finance toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources