Parse a natural language expense description into structured fields. Does NOT add the expense — just returns the parsed fields for review. Example: "Lunch at Chipotle $15.50 today" → {merchant: "Chipotle", total: 15.50, ...}
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Natural language expense (e.g., "Coffee at Starbucks $6.50 yesterday") |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output 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: +nullDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry readOnlyHint=true and destructiveHint=false, and the description's explicit 'Does NOT add the expense' aligns with and reinforces that safety profile. It adds behavioral value beyond the annotations by showing the return shape in the example, which matters here because there is no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with zero fluff: purpose, negative-scope disclaimer, and an example. The most decision-relevant information ('Does NOT add the expense') is front-loaded right after the verb, and every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter read-only parser, the description covers what, why, and what not, with a worked example. The only meaningful gap is that no output schema exists and the example shows a partial field set with an ellipsis, so an agent cannot know the full set of returned fields or edge-case behavior, such as an unparseable string.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single text parameter, establishing a baseline of 3. The description adds meaning beyond the schema by demonstrating an input-to-output transformation (a full natural-language phrase mapping to structured fields), which clarifies what form of 'text' is expected.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb and resource ('Parse a natural language expense description into structured fields') and immediately clarifies the tool's non-goal ('Does NOT add the expense'), which separates it from the many add_*/submit_* siblings in the list. The concrete worked example ('Lunch at Chipotle $15.50 today' → {merchant...}) leaves no ambiguity about what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'just returns the parsed fields for review' implicitly tells an agent this is a preview/parse step rather than a recording step, which helps an agent decide between parse_expense and add_cash_expense/submit_receipt. It stops short of a 5 because no alternative tool is named explicitly, so the routing is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are explicitly scoped, but several analytics/retrieval tools overlap in purpose, such as get_spending_summary vs get_deep_analytics vs get_monthly_books_review, and generic search vs search_expenses vs search_knowledge. The detailed descriptions help, but an agent still has to carefully choose between near-equivalent options like correct_expenses vs update_expense and the three add_income variants.
Tool names consistently use lower_snake_case with a recognizable verb prefix: get_*, list_*, add_*, create_*, check_*, scan_*, search_*, and whatif_*. Minor exceptions like fetch and search are still terse retrieval verbs rather than a different naming style, so the overall pattern is predictable.
With 59 tools, this exceeds the 50+ threshold for an extreme tool count and creates a heavy selection surface for an agent. Even though ExpenseBot covers many subdomains, many get_/list_/add_ variants could be consolidated into fewer parameterized tools. The count undermines the otherwise clear naming structure.
The surface is strong for creating, reading, and updating expenses, reports, invoices, and Gmail scans, but there are notable lifecycle gaps: no delete/void tools for expenses, income, reports, or invoices, and no update tool for income. Several descriptions explicitly redirect unsupported edits to the web app, confirming that the assistant cannot complete those workflows directly.