Parse invoice text into structured JSON with line items, totals, tax, validation. Detects arithmetic errors, extracts bank details.
Scored across 1 tool
With only a single tool, there is no possibility of overlap or misselection. Its purpose is unambiguous: parse invoice text into structured JSON.
The single tool name parse_invoice follows a clear verb_noun convention. Consistency is trivially satisfied with one tool.
A single tool is thin for a server, though the narrow scope (invoice parsing) makes it plausible. It falls in the borderline 1-2 tool range rather than being well-scoped with 3+ tools.
The tool covers extraction, validation, line items, totals, tax, currency, and bank details, which is strong core coverage for parsing. Minor gaps like batch parsing or configurable output options are absent but not critical.
Parse invoice text into structured JSON with line items, totals, tax, currency, and validation. Detects arithmetic errors, missing fields, and extracts bank details. Useful for accounting automation, AP/AR, expense management.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Raw invoice text |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose useful behavioral detail beyond the name: error detection (arithmetic errors, missing fields) and bank-detail extraction. However, it says nothing about non-mutating/read-only nature, behavior on non-invoice input, confidence/accuracy limits, or size/length constraints on the input text.
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, front-loaded with the core capability and output contents. The closing use-case list is mildly promotional rather than operational, but overall it is tight and wastes little space.
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 single-parameter tool with no output schema, the description usefully sketches the return contents (line items, totals, tax, currency, validation, bank details), which is exactly what the missing output schema would otherwise leave unknown. Only the input-format expectations and failure modes remain uncovered.
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?
There is a single parameter ('text') with 100% schema description coverage, so the schema already documents it as 'Raw invoice text'. The description adds no format guidance (plain text vs OCR output vs PDF text layer) beyond what the schema states, so 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?
States a specific verb (parse) and resource (invoice text) and enumerates the output shape: structured JSON with line items, totals, tax, currency, and validation. There are no siblings to disambiguate from, so the scope statement alone is sufficient for an agent to know exactly what this 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 final sentence names domains (accounting automation, AP/AR, expense management), which implies when the tool is relevant, but it gives no explicit trigger conditions, prerequisites, or alternatives. With no sibling tools, there is nothing to route against, so implied usage is the ceiling here.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
parse_invoice
Add one secure layer between your agents and this server.