Skip to main content
Glama
jaakla

Merit MCP

Merit Write Sales Confirm

merit_write_sales_confirm
Destructive

Execute pending sales invoice actions after providing confirmation code and confirming the operation.

Instructions

Confirmed mutating tool. Executes a previously previewed write operation from merit_write_sales when called with confirmation_code and confirmed=true. Create, delete, and deliver sales invoices. Actions: sales_invoice_create: Create a draft sales invoice through Merit v1 /sendinvoice. The payload is passed through to Merit and must use the create schema, not the invoice_get response shape. Required shape: Customer.Id, DocDate, TransactionDate, and DueDate as YYYYMMDD strings, mandatory string InvoiceNo, CurrencyCode (usually EUR), PriceInclVat (usually false), optional FComment footer note, singular InvoiceRow list, TaxAmount list, and TotalAmount. Each InvoiceRow item must use Item={Code, Description, UOMName}, Quantity, Price, row-level TaxId GUID, and Account. Gotchas: use InvoiceRow (singular), not InvoiceRows; Merit will not auto-assign InvoiceNo, so read merit_read_sales action=invoices_list and use the next integer; UOMName belongs inside Item; use Account, not AccountCode; use TaxId GUID, not TaxName or TaxPct; TaxAmount is required even for zero VAT, e.g. [{'TaxId': '', 'Amount': 0}]; TotalAmount is required and should match the row Price x Quantity total. For Googolplex no-VAT 'Ei ole käive', the known TaxId is 7e170b45-fe96-4048-b824-39733c33e734; verify with merit_read_master_data action=taxes_list if it changes. Do not include DelivNote/delivnote=true in invoice creation payloads; invoices should remain undelivered drafts and delivery is handled manually in Merit.; sales_invoice_delete: Delete a sales invoice by id.; credit_invoice_create: Create a credit invoice.; sales_invoice_send_email: Send a sales invoice by email. This delivers the invoice; do not use it in the normal draft creation flow where delivery is handled manually in Merit. Keep delivnote=false unless the user explicitly asks for delivery note mode without prices.; sales_invoice_send_einvoice: Send a sales invoice as e-invoice. This delivers the invoice; do not use it in the normal draft creation flow where delivery is handled manually in Merit. Keep delivnote=false unless the user explicitly asks for delivery note mode without prices.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes
idNo
filtersNo
payloadNo
add_attachmentNo
delivnoteNo
bank_idNo
confirmation_codeNo
confirmedNo
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate destructiveHint=true, and the description reinforces this by stating it is a 'mutating tool' and detailing operations. It adds many behavioral gotchas (e.g., payload shape, required fields, limitations like not including DelivNote) that go beyond annotations, ensuring the agent understands side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is thorough but overly long and dense, mixing general purpose with detailed payload examples. While front-loaded with the main purpose, it could benefit from more structured formatting (e.g., bullet points) to improve readability without losing detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, usage, and parameter details comprehensively but lacks explanation of return values or error handling, which is significant given no output schema. It also omits descriptions for some schema fields like filters and add_attachment, relying on inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description extensively explains the payload structure for each action and clarifies the use of confirmation_code, confirmed, and delivnote. However, it does not directly describe all parameters (e.g., filters, id, add_attachment) with equal depth, though their context is inferable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it is a 'Confirmed mutating tool' that executes previously previewed write operations from merit_write_sales. It lists specific actions (create, delete, credit, send email, send e-invoice) and distinguishes itself from the sibling tool merit_write_sales by requiring confirmation_code and confirmed=true.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly provides when to use (only after preview from merit_write_sales) and when not to use (e.g., do not use send email in normal draft creation). It gives detailed context on alternative flows and prerequisites like confirmation_code and confirmed flag.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jaakla/merit_api'

If you have feedback or need assistance with the MCP directory API, please join our Discord server