ExpenseBot

send_report_to_accounting

Review and then post an ExpenseBot report to the owner's accounting destination. STEP 1: call with provider, reportId and optional mode/mappings, without confirm. The server reads the live report and destination, applies Omit/Personal/split/date/currency rules, checks Zoho bank-feed matches, and returns the complete proposal plus proposalId. NOTHING is posted in step 1. Show the complete proposal and ask for approval. STEP 2: call with only provider, proposalId and confirm:true. The server posts only the frozen, account-bound proposal, revalidates live state, and rejects changed reports or mappings. Never add mapping fields to the confirmation call. Owner accounts only; acting for a client is not supported. Agent-driven posting is currently available only for Zoho Books (zoho_books); QuickBooks Online, Xero, Wave and FreeAgent are not accepted yet because their previews cannot freeze/revalidate the plan shareReport executes. Use those providers' web flows.

Input Schema

Name	Required	Description
`mode`	No	Step 1 only (Zoho Books): automatic document treatment, paid expenses, or bills.
`confirm`	No	Step 2 only: true posts the exact staged proposal. No other options may change.
`provider`	Yes	Accounting destination provider. Agent-driven posting is currently available only for Zoho Books.
`reportId`	No	Step 1 only: ExpenseBot report ID owned by the signed-in account.
`proposalId`	No	Step 2 only: proposalId returned by the read-only preview.
`forceRepush`	No	Step 1 only: explicitly include disclosed uncertain prior outcomes in the frozen proposal.
`taxMappings`	No	Step 1 only: observed tax-rate string to live destination tax ID overrides.
`accountMappings`	No	Step 1 only: ExpenseBot category to live destination account ID overrides.
`reportingTagMappings`	No	Step 1 only: ExpenseBot tag to live destination reporting-tag option.

Output Schema

Name	Required	Description	Default
`phase`	Yes
`units`	No
`counts`	No
`created`	No
`success`	Yes
`provider`	Yes
`reportId`	No
`expiresAt`	No
`proposalId`	Yes
`finalAnswer`	No
`organization`	No
`matchedExisting`	No
`omittedExpenses`	No
`idempotentReplay`	No
`responseGuidance`	No
`confirmationContract`	No
`confirmationQuestion`	No
`confirmationRequired`	No
`skippedAlreadyPushed`	No
`reconciliationRequired`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "allOf": [
+    {
+      "if": {
+        "properties": {
+          "phase": {
+            "const": "preview"
+          }
+        },
+        "required": [
+          "phase"
+        ]
+      },
+      "then": {
+        "required": [
+          "expiresAt",
+          "confirmationRequired",
+          "confirmationQuestion",
+          "confirmationContract"
+        ]
+      }
+    },
+    {
+      "if": {
+        "properties": {
+          "phase": {
+            "const": "completed"
+          }
+        },
+        "required": [
+          "phase"
+        ]
+      },
+      "then": {
+        "required": [
+          "reportId",
+          "finalAnswer",
+          "responseGuidance"
+        ]
+      }
+    }
+  ],
+  "properties": {
+    "confirmationContract": {
+      "type": "string"
+    },
+    "confirmationQuestion": {
+      "type": "string"
+    },
+    "confirmationRequired": {
+      "type": "boolean"
+    },
+    "counts": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "created": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "expiresAt": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "finalAnswer": {
+      "type": "string"
+    },
+    "idempotentReplay": {
+      "type": "boolean"
+    },
+    "matchedExisting": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "omittedExpenses": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "organization": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "phase": {
+      "enum": [
+        "preview",
+        "completed"
+      ],
+      "type": "string"
+    },
+    "proposalId": {
+      "type": "string"
+    },
+    "provider": {
+      "type": "string"
+    },
+    "reconciliationRequired": {
+      "type": "boolean"
+    },
+    "reportId": {
+      "type": "string"
+    },
+    "responseGuidance": {
+      "type": "string"
+    },
+    "skippedAlreadyPushed": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "success": {
+      "type": "boolean"
+    },
+    "units": {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "success",
+    "phase",
+    "provider",
+    "proposalId"
+  ],
+  "type": "object"
+}

Changed1 schema field changedAug 25, 2026

changedOutput schema / (root)

Previous value: -{
-  "additionalProperties": true,
-  "description": "Standard ExpenseBot tool result envelope. `message` is the human-readable summary the AI cites; `data` is the structured payload (totals, breakdowns, ids, etc.). On failure, `success` is false and `error` carries a code/message/hint triple.",
-  "properties": {
-    "data": {
-      "additionalProperties": true,
-      "description": "Structured payload. Shape varies per tool — common keys: total, breakdown, comparison, sampleMeta, ids, expenseId, reportId, signupUrl, results.",
-      "type": "object"
-    },
-    "error": {
-      "additionalProperties": true,
-      "description": "Present only when success === false.",
-      "properties": {
-        "code": {
-          "type": "string"
-        },
-        "hint": {
-          "type": "string"
-        },
-        "message": {
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "message": {
-      "description": "Human-readable result text. Always present on success; prefer rendering this verbatim before any further reasoning.",
-      "type": "string"
-    },
-    "sampleMeta": {
-      "additionalProperties": true,
-      "description": "Set when the underlying dataset was truncated. isTruncated=true means the agent saw a sample of `sampleCount` of `totalCount` rows; aggregate totals are still accurate.",
-      "properties": {
-        "isTruncated": {
-          "type": "boolean"
-        },
-        "sampleCount": {
-          "type": "integer"
-        },
-        "totalCount": {
-          "type": "integer"
-        }
-      },
-      "type": "object"
-    },
-    "success": {
-      "description": "False on tool errors; check before reading `data`.",
-      "type": "boolean"
-    }
-  },
-  "type": "object"
-}New value: +null

Changed2 schema fields changedAug 23, 2026

changedInput schema / properties / mode / description

Previous value: -"Step 1 only: automatic document treatment, paid expenses, or bills."New value: +"Step 1 only (Zoho Books): automatic document treatment, paid expenses, or bills."

changedInput schema / properties / provider / description

Previous value: -"Accounting destination provider."New value: +"Accounting destination provider. Agent-driven posting is currently available only for Zoho Books."

Changed2 schema fields changedAug 22, 2026
- addedInput schema / properties / reportingTagMappings / additionalProperties / properties / optionId / description
```
Added value: +"Live option ID belonging to tagId, returned in the step-1 proposal."
```
- addedInput schema / properties / reportingTagMappings / additionalProperties / properties / tagId / description
```
Added value: +"Live accounting-provider reporting-tag ID returned in the step-1 proposal."
```
AddedAug 13, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare readOnlyHint=false / destructiveHint=false / openWorldHint=true; the description adds the substantive behavior: step 1 posts nothing, the proposal is frozen and account-bound, step 2 revalidates live state and rejects changed reports or mappings, and mapping fields must not be resent. It also discloses the authorization constraint (owner-only) and the hard provider limitation. This is context the structured fields cannot supply.

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?

Front-loaded with the verb and resource, then cleanly segmented into STEP 1 and STEP 2 with an explicit warning sentence. Every sentence carries operational weight, though the repeated emphasis that nothing is posted and the mapping-field prohibition restate adjacent sentences, adding some density without new information.

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 9-parameter, two-phase mutation tool with nested mapping objects and an output schema, the description covers the full decision surface: gating conditions, mutation semantics, revalidation behavior, authorization scope, and provider limits. Return-value shapes are correctly left to the output schema.

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 already 100%, so the baseline is 3, but the description adds cross-parameter semantics the schema cannot express: which parameters are step-1-only versus step-2-only, and the prohibition on adding mapping fields to the confirmation call. It does not explain forceRepush's 'disclosed uncertain prior outcomes' meaning beyond the schema's own wording, so it stops short of a 5.

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?

States a specific verb and resource ('post an ExpenseBot report to the owner's accounting destination') and frames the operation as a staged review-then-post workflow. It explicitly distinguishes itself from shareReport by naming that sibling when explaining why other providers are unsupported. An agent can identify the tool's job without opening the 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 an explicit two-step protocol with which parameters belong to which step, and the condition that gates step 2 (human approval of the complete proposal). It also states exclusions: owner accounts only, no acting for a client, and Zoho Books only with named providers relegated to their web flows. Nothing about when to call is left to inference.

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

All ExpenseBot 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.