Skip to main content
Glama
cotletdev

Contractor Foreman MCP Server

by cotletdev

Send invoice

send_invoice
Destructive

Emails an invoice PDF to the customer or specified recipients. Use it to deliver billing directly from Contractor Foreman; a due date is required and status must be updated separately.

Instructions

Emails the invoice as a PDF to the customer or to the addresses you give.

Sends the invoice PDF by email from Contractor Foreman, as the panel's View/Email PDF does. Without to it goes to the invoice's customer, and a customer without an email stops the call. The invoice needs a due date (update_invoice). Sending does not change the status: update_invoice with status submitted marks it sent.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoRecipient emails. Default: the invoice's customer.
copy_meNo
messageNoEmail text above the PDF.
subjectNoDefault: the app's 'Invoice #n'.
invoice_idYesFrom list_invoices or create_invoice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructive/openWorld/non-idempotent, and the description adds real context beyond them: sending does NOT change invoice status, and a customer lacking an email aborts the call. It does not explain the irreversibility that the destructiveHint implies, or error behavior for bad addresses.

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

Conciseness4/5

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

Three sentences, front-loaded with the core action, and the status clarification earns its place. The comparison to the panel's View/Email PDF is a reference an agent cannot act on and is mild filler.

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

Completeness4/5

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

With no output schema, the description covers preconditions, recipient defaults, blocking conditions, and post-send state so an agent can call it correctly. Minor gaps remain around failure modes beyond the missing-customer-email case.

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

Parameters3/5

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

Schema coverage is 80%, so most semantics are already documented. The description largely restates the `to` default that the schema already states, adds the no-email failure mode, but says nothing about copy_me or message.

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?

States a precise verb and resource: the invoice PDF is emailed to the customer or supplied addresses. It also distinguishes itself from status-changing siblings by naming update_invoice as the way to mark an invoice sent.

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

Usage Guidelines4/5

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

Gives clear preconditions (invoice needs a due date) and routes to update_invoice for the follow-up status change, plus the blocking case of a customer with no email. It stops short of explicitly naming when to prefer send_estimate or send_change_order instead.

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

Deploy Server

Other Tools