AU GST/ABN receipt extraction — assigns entertainment/ITC tax codes per line, not just OCR.
Scored across 1 tool
With only one tool, there are no other tools to disambiguate against uppercase, but the purpose is singular and distinct. However, the score is low because the criterion asks whether an agent can tell tools apart; with one tool, there is no possible confusion but also no need for disambiguation, so it gains minimal credit.
The single tool name 'extract_receipt' follows a clear verb_noun pattern, which is consistent with common conventions. However, with only one tool, there is no pattern to compare against, making consistency somewhat moot but acceptable.
A single tool for a domain that likely includes multiple operations (e.g., list, delete, validate) feels thin. While some servers are naturally single-purpose, receipt extraction typically involves more than just extraction, making this count borderline low.
The server only offers extraction, missing likely complementary operations such as listing past extractions, updating extracted receipts, or deleting them. This creates a dead-end where extracted data goes nowhere, significantly limiting the tool's usefulness in a broader workflow.
Extracts a structured Receipt (vendor, ABN-checked, GST-aware line items and totals) from a base64-encoded receipt or invoice image/PDF.
| Name | Required | Description | Default |
|---|---|---|---|
| mime_type | Yes | ||
| document_base64 | Yes |
| Name | Required | Description |
|---|---|---|
| date | Yes | |
| totals | Yes | |
| vendor | Yes | |
| line_items | Yes | |
| schema_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint=true, so the tool is safe for reading. The description adds behavioral context such as ABN-checking and GST-awareness, which are not in annotations. It does not cover rate limits or authentication, but given annotations provide a baseline, this is sufficient.
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?
The description is a single, direct sentence of 17 words with no fluff. It is front-loaded with the core action and efficient in conveying the tool's purpose.
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?
Given only two parameters, no siblings, and an output schema (not shown), the description covers the essential inputs and outputs. Missing details like allowed MIME types are minor. The description is generally complete for the tool's complexity.
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 0%, so the description must compensate. It implicitly explains that document_base64 is the base64-encoded content and mime_type is its type, but it does not list allowed MIME types or describe the base64 format. The description adds some meaning but not full clarity.
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 clearly states the tool extracts a structured Receipt with vendor, ABN-checked, and GST-aware details from base64-encoded images or PDFs. It provides specific verb and resource, and since there are no sibling tools, differentiation is not needed.
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 description implies usage when a receipt or invoice image is available but does not provide explicit guidance on when to use this tool versus alternatives (none exist) or when not to use it. No prerequisites or failure scenarios are mentioned.
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.
extract_receipt3 fields changedOutput schema / properties / line_items / items / properties / confidenceAdded value: +{
+ "type": "number"
+}Output schema / properties / line_items / items / properties / rationaleAdded value: +{
+ "type": "string"
+}Output schema / properties / line_items / items / requiredPrevious value: -[
- "description",
- "qty",
- "unit_price",
- "gst",
- "tax_code"
-]New value: +[
+ "description",
+ "qty",
+ "unit_price",
+ "gst",
+ "tax_code",
+ "confidence",
+ "rationale"
+]extract_receiptInvoice and receipt extractor: reads PDF and image invoices/receipts with AI, pulling date…
PDF tools + invoice extraction, bank statement parsing, GST reconciliation & GSTIN validation.
Extract, search and tag any document: invoices, receipts, contracts, templates. OAuth or API key.
Invoices and other financial documents to rows: upload, say what to extract, read the rows.
Add one secure layer between your agents and this server.
