Skip to main content
Glama
gray-wilbee

fub-mcp

by gray-wilbee

create_template

Create a new email template in Follow Up Boss CRM by providing a name, subject, and HTML body with merge field placeholders for personalization.

Instructions

Create a new email template. (POST /templates) body is the raw HTML of the email template directly — there is no separate isHtml/html flag for templates (unlike notes, which need isHtml=true explicitly). FUB templates support %merge_field% placeholders that FUB substitutes when a human actually sends the template (not by this tool — this just saves the template text as-is). Reference: Contact: %contact_name% (full), %contact_first_name%, %contact_last_name%, %contact_email%, %contact_phone%, %contact_address%, %contact_street%, %contact_city%, %contact_state%, %contact_zipcode%, %contact_country%, %contact_rels_first_name% (first names of the contact's linked relationships, e.g. spouse/family added via peopleRelationships). Company (from Admin > Company settings): %company_name%, %company_phone%. Agent / Lender / Sender — same field set, swap the prefix (agent = assigned agent, lender = assigned lender, sender = whoever is actually sending this particular message, which may be neither): %agent_name%, %agent_first_name%, %agent_last_name%, %agent_email%, %agent_phone% (the FUB-assigned calling/texting number), %agent_mobile_phone% (their real/personal number), %agent_merge_field_1% (one free-form field each user sets in My Settings > Other Settings > Edit User Merge Field — commonly a booking link or social profile). ⚠️ %_phone% vs %mobile_phone% is genuinely ambiguous — always confirm with the user which one they mean before using either; picking wrong sends the recipient the wrong callback number. Inquiry (how the contact became a lead, e.g. clicking "Get more info" on a listing site): %inquiry_address%, %inquiry_address_url% (only if the lead source provided one), %inquiry_address_preview% (renders an HTML photo+link box — email only, meaningless in a plain-text SMS template). Recently viewed (populated only when synced with a provider that shares property views): %viewed_address%, %viewed_address_url%, %viewed_address_preview%, %last_5_preview% (up to 5 as HTML boxes, email only). Other: %source_name% (lead source, e.g. "Zillow" — "I saw your inquiry on %source_name%"), %greeting_time% ("Morning"/"Afternoon"/"Evening" based on send time — "Good %greeting_time%, %contact_first_name%"), %tour_time% (populated if the contact scheduled a tour via Zillow). Custom fields: %custom% (e.g. %custom_website%, %custom_birthday%, %custom_spouse_name%). Call list_custom_fields to confirm a field exists — but note its API name (e.g. customBirthday, camelCase) and its merge-field name (%custom_birthday%, snake_case) are different spellings of the same field, and there's no API that returns the merge-field spelling directly, so confirm the exact form with the user (or FUB's own Merge Fields dropdown in the template composer) if it's not obvious from the label. A merge field with no value for a given contact is simply left blank when the template is used — not an error, not a visible placeholder.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyYesThe HTML body of the email template.
nameYesThe name of the new email template.
subjectYesThe email subject used when this email template is selected.
isSharedNoIndicates whether this email template should be shared with other users in the same Follow Up Boss account.
extraBodyNoExtra raw JSON body fields not explicitly listed above — e.g. custom.* fields when creating/updating people or deals. Keys and values are sent as-is.
extraQueryNoExtra raw query parameters not explicitly listed above — e.g. FUB custom field filters like custom.ClosingDate on /people or /deals. Keys and values are sent as-is.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden. It discloses key traits: the tool doesn't substitute merge fields at save time, FUB substitutes them later when a human sends, empty merge fields are left blank rather than erroring, and there is no separate HTML flag. It could additionally mention response shape or auth requirements, but the behavioral core is well covered.

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?

The description is long, but it is front-loaded with the core purpose and body semantics, then organized into clear merge-field categories. The length is largely justified by the complexity of FUB merge fields; the warning about ambiguous phone fields earns its place. It loses a point because it could be tightened without losing essential guidance.

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?

Given no annotations and no output schema, this description is unusually complete for invocation: it covers endpoint, required parameters, body format, placeholder behavior, and empty-field edge cases. The main gaps are lack of explicit return-value information and no mention of `isShared` behavior beyond the schema, but those are minor relative to the rich context provided.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description goes far beyond: it explains that `body` is raw HTML, enumerates the full merge-field vocabulary with contextual warnings about ambiguous phone fields, and describes custom field placeholder conventions. This is exactly the kind of parameter meaning an agent needs beyond the schema.

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 opens with a specific verb, resource, and endpoint: 'Create a new email template. (POST /templates)'. It clearly distinguishes this from updating templates and from text-message templates by emphasizing email and raw HTML body. Even without reading the schema, an agent knows exactly what the tool does.

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?

The description clearly frames when to use this tool: when creating a new email template via POST /templates. It adds useful guidance by contrasting with notes ('unlike notes, which need isHtml=true explicitly') and by clarifying that this tool only saves text, not sends it. It doesn't explicitly route to sibling tools like update_template or create_text_message_template, but the usage context is clear.

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