Expense tracker
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | The expenses to total. A refund is a negative amount. | |
| mergeCategories | No | true treats categories that differ only in case or surrounding spaces as one. Default false (exactly as sent). |
Changes observed during successful MCP inspections.
Input schema / properties / items / descriptionAdded value: +"The expenses to total. A refund is a negative amount."Input schema / properties / items / items / properties / dateAdded value: +{
+ "description": "Optional date, YYYY-MM-DD. When any item has one, the response adds byMonth totals.",
+ "pattern": "^\\d{4}-\\d{2}-\\d{2}",
+ "type": "string"
+}Input schema / properties / items / items / properties / descriptionAdded value: +{
+ "description": "Optional note; not used in the totals.",
+ "maxLength": 200,
+ "type": "string"
+}Input schema / properties / mergeCategoriesAdded value: +{
+ "description": "true treats categories that differ only in case or surrounding spaces as one. Default false (exactly as sent).",
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations fully declare the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is low. Even so, the description adds nothing beyond the name — it doesn't mention that the tool is a pure computation over caller-supplied data with no side effects, nor how category merging affects the totals.
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?
Two words is not conciseness — it's under-specification. There is no front-loaded statement of purpose or scope, and nothing in the description earns or lacks a place because nothing was written.
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 tool taking a nested array of expense records with aggregation semantics and no output schema, the description should at least state that it computes totals and what triggers the byMonth breakdown. All of that is left to the schema, leaving an agent with no narrative confirmation of what the call produces.
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 description coverage is 100%, so the schema already documents items, the date-triggered byMonth totals, negative-amount refunds, and mergeCategories semantics. The description adds no parameter meaning of its own; baseline 3 applies.
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?
"Expense tracker" restates the tool name rather than stating a specific verb and resource. It doesn't say the tool totals a list of expenses, nor does it distinguish it from close siblings like business_receipt or business_invoice_totals.
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?
No when-to-use, when-not-to-use, or alternative-tool guidance is given. The only hints about behavior (date-triggered monthly totals, negative amounts as refunds, category merging) live entirely in the schema, not the description.
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.