This record as markdown: /tools/ghl/send-estimate.md
What send_estimate does on Ghl
AI agents use send_estimate to create or update resources in Ghl, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ghl environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
altId | string | — | Location ID |
emailTo | string | — | Email address to send to |
message | string | — | Email message |
subject | string | — | Email subject |
estimateId | string | Yes | Estimate ID |
Parameters from the server's own tool schema.
Why send_estimate is rated Medium
Sending an estimate is a reversible write operation that creates or modifies data (estimate status, delivery log, customer communication history) without permanently destroying data or executing arbitrary code. While it has business significance, it lacks the irreversibility of Destructive actions and the financial commitment of a Financial transaction (estimates are proposals, not executed payments).
From the tool's definition Tool name 'send_estimate' and description 'Send an estimate to customer' indicate creation and transmission of a business document to an external party. This modifies state (estimate sent/delivered) and creates a record of the transaction.
Attacks that exploit this kind of access
The rule that runs send_estimate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ghl, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For send_estimate, this is the rule to start with:
send_estimate stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ghl, apply this rule, and every send_estimate call is checked against it from then on.
Questions about send_estimate
Send an estimate to customer. It is categorised as a Write tool in the Ghl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
send_estimate accepts 5 parameters: altId, emailTo, message, subject, estimateId. Required: estimateId. The full parameter table on this page comes from the server's own tool schema.
Register the Ghl MCP server in PolicyLayer and add a rule for send_estimate: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ghl. Nothing to install.
send_estimate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the send_estimate rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for send_estimate. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
send_estimate is provided by the Ghl MCP server (ghl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ghl, and thousands of servers like it.
This server
Across the catalogue