Make invoice, quote and receipt PDFs from a chat: totals, tax, 26 currencies. Free, nothing stored.
Scored across 1 tool
There is only one tool, so there is no possible confusion or misselection between tools. An agent cannot pick the wrong tool here.
The single tool 'create_invoice' follows a clear verb_noun snake_case convention. With only one name there is no inconsistency to detect.
A single tool for an invoice-making server is on the thin side; while it is a focused, well-scoped capability, there is no separate operation for listing, editing, or managing invoices, leaving the surface narrow for its stated purpose.
The tool covers creation, calculation (line totals, tax, discount, shipping), and PDF output for invoices, quotes, estimates and receipts, which is a solid core. However, there are notable gaps: no way to update, void, delete, list, or retrieve previously generated invoices, so lifecycle coverage is incomplete.
Use this when the user wants to make, create, generate or send an invoice, bill, quote, estimate or receipt, or asks for an "invoice PDF" or "invoice template filled in". Calculates line totals, tax, discount and shipping and returns a download link to a print-ready PDF plus the totals. Ask for missing essentials (who it is for and the items with prices) before calling; the seller details are optional.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | The customer | |
| date | No | Issue date YYYY-MM-DD (default today) | |
| from | No | The seller (the user's business) | |
| type | No | invoice | |
| items | Yes | ||
| notes | No | Thank-you note, bank details or terms | |
| style | No | ||
| number | No | Document number, e.g. INV-0042 | |
| dueDate | No | Exact due date YYYY-MM-DD, if given | |
| currency | No | ISO code, e.g. USD, EUR, GBP, CAD, AUD | USD |
| shipping | No | ||
| taxLabel | No | Tax, VAT, GST, Sales tax… | |
| dueInDays | No | Payment terms in days (0 = due on receipt). Default 14. | |
| paperSize | No | ||
| paymentLink | No | An https payment link to print on the PDF (optional) | |
| paymentMethod | No | Receipts only: how it was paid | |
| discountPercent | No | Discount on the whole document |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), and the description usefully adds that this is a stateless generator returning a download link rather than persisting a record. It also discloses that totals, tax, discount and shipping are computed. It stops short of noting the 60-item cap or whether generated documents are retrievable later.
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 sentences plus a short clause, with the trigger condition and output described up front. The synonym list is long but serves recall; there is no filler or repetition, though the first sentence is dense enough that it could be split for scannability.
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 17-parameter tool with nested objects and no output schema, the description carries the important missing pieces: what the tool returns (link + totals) and the prerequisite inputs. It omits operational limits (max 60 items) and defaults, which are the only notable gaps.
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 71%, just under the high-coverage threshold, and the description only touches the most important parameters: required 'items' with prices and the optional 'to'/'from' seller details. It adds no meaning for the other 14 parameters (tax, shipping, currency, style, dueInDays, paperSize, paymentLink, etc.) beyond what the schema already documents.
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 (make/create/generate/send) and resource (invoice, bill, quote, estimate, receipt) and explicitly covers user phrasings like 'invoice PDF'. It also declares the output artifact (print-ready PDF download link plus totals), so an agent knows exactly what the tool produces without opening the schema.
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?
Explicit trigger conditions are given ('when the user wants to make, create, generate or send...'), plus a behavioral precondition: ask for missing essentials (recipient and priced items) before calling, with seller details marked optional. No sibling tools exist, so no alternative routing is needed.
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.
create_invoice1 field changedInput schema / properties / items / examplesAdded value: +[
+ [
+ {
+ "description": "Web design (hours)",
+ "quantity": 12,
+ "unitPrice": 85
+ }
+ ]
+]create_invoiceMake PDF invoices from your AI chat: clients, numbering, VAT, overdue reports. All data is local.
Freelancer invoice generator: line items, tax, totals, PDF - issued from a chat message.
Create PDF invoices from your AI chat: clients, numbering, VAT, overdue reports. All data is local.
Create PDF invoices from your AI chat: clients, numbering, VAT, overdue reports. All data is local.
Add one secure layer between your agents and this server.