ExpenseBot

get_pnl

Read-only

Compute Profit & Loss (P&L / net income / margin) by combining the Income tab with expense tabs. Examples: 'am I profitable this year', 'P&L for Q1', 'net income last quarter', 'what's my margin', 'P&L this year vs last' (YoY). Supports period comparison — YoY, MoM, QoQ, same-month-prev-year. Margin renders as multiplier in loss territory ('expenses 5.4× revenue') so the user gets a readable signal instead of '-436.9% margin'. Returns: { message, data: { revenue, expenses, netIncome, margin, comparison?, sampleMeta? } }.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	No	Natural language P&L question (e.g., 'P&L for Q1 2025', 'am I profitable')
`dateRange`	No	Time period filter. Use exactly one variant — pick the shape that matches the user's phrasing.
`clientEmail`	No	Client account email. Accountants may use this only for an accepted ExpenseBot client.

Output Schema

TableJSON Schema

Name	Required	Description
`data`	No	Inline branch: computed analytics, or null when no spreadsheet / no data.
`type`	No	Async branch only: "analytics_pending" — poll pollEndpoint or call poll_analytics with jobId.
`jobId`	No	Async branch only.
`message`	No	Human-readable narrative (both branches).
`success`	No	Async branch only.
`response`	No	Chat alias of message.
`pollEndpoint`	No	Async branch only.
`pollInterval`	No	Async branch only: milliseconds.
`estimatedTime`	No	Async branch only: seconds.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Two branches. Async: type='analytics_pending' with jobId — poll poll_analytics until complete. Inline: message + data with the computed analytics (data may be null when there is no spreadsheet or no data yet). success is present only on the async branch.",
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "description": "Inline branch: computed analytics, or null when no spreadsheet / no data.",
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "estimatedTime": {
+      "description": "Async branch only: seconds.",
+      "type": "number"
+    },
+    "jobId": {
+      "description": "Async branch only.",
+      "type": "string"
+    },
+    "message": {
+      "description": "Human-readable narrative (both branches).",
+      "type": "string"
+    },
+    "pollEndpoint": {
+      "description": "Async branch only.",
+      "type": "string"
+    },
+    "pollInterval": {
+      "description": "Async branch only: milliseconds.",
+      "type": "number"
+    },
+    "response": {
+      "description": "Chat alias of message.",
+      "type": "string"
+    },
+    "success": {
+      "description": "Async branch only.",
+      "type": "boolean"
+    },
+    "type": {
+      "description": "Async branch only: \"analytics_pending\" — poll pollEndpoint or call poll_analytics with jobId.",
+      "type": "string"
+    }
+  },
+  "required": [],
+  "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

First observedAug 10, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false), and the description adds genuinely non-obvious behavior: margin is rendered as a multiplier in loss territory ('expenses 5.4× revenue') rather than a negative percentage, and comparison output is conditional. It does not mention auth/permission nuances or data-freshness limits.

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-loads the core definition, then example phrasings, then the return shape — a sensible priority order with no filler sentences. The inline example list is somewhat long, but each example earns its place by teaching the NL query surface an agent must match.

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 the brief returns summary ({ message, data: {...} }) is supplementary rather than required, and the description covers the data sources, comparison support, and the margin edge case. Missing only the when-not-to-use boundary versus per-tag and analytics siblings.

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% and the dateRange oneOf variants are fully self-documenting, so the baseline is 3. The description's restatement of example query strings and period-comparison semantics adds only marginal meaning beyond the schema and does not clarify e.g. precedence between 'query' and 'dateRange' or the clientEmail authorization rule.

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 ('Compute Profit & Loss ... by combining the Income tab with expense tabs') and defines scope (revenue minus expenses plus margin), which inherently separates it from single-axis siblings like get_income_summary and get_spending_summary. The natural-language example queries ('am I profitable this year', 'what's my margin') make the intent unmistakable.

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?

Gives strong contextual triggers via example phrasings and enumerates supported comparison modes (YoY, MoM, QoQ, same-month-prev-year). It does not, however, state when NOT to use it or name alternatives such as get_per_tag_pnl for per-tag breakdowns or get_deep_analytics, so routing against close siblings 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.