HelpWell

Create a proactive message

create_proactive_message

Saves a new chat message, pop-up or banner as a draft. Visitors see nothing until publish_proactive_message. write_proactive_message_copy can draft the words.

Input Schema

Name	Required	Description
`goal`	No	What counts as success: { event (a journey trigger name such as page.visited, or null), name (for custom.event), days, stop: stop showing it to people who reached it }.
`kind`	Yes
`name`	Yes	Internal name.
`pages`	No	Page paths: { include: ["/pricing", "/docs/**"], exclude: [] }. No includes means every page.
`content`	No	By kind. chat: { text (markdown, at most 300 chars, {{first_name}} works), sender: {type:"agent"} \| {type:"member",userId} \| {type:"team",name}, display: "bubble"\|"messenger", buttons: [{label, action: url\|chat\|article\|dismiss\|reply, value}], replyable }. popup: { slides: [{ title, text, button: {label, action, value} \| null, media: null }], size: small\|medium\|large, layout: top\|side\|background, dismissible }. banner: { text (at most 120 chars), position: top\|bottom, style: inline\|floating, tone: accent\|neutral\|warning, cta: { type: none\|link\|button, label, url }, dismissible }.
`trigger`	No	Popups and banners only: when it shows. { type: "load" } \| { type: "delay", seconds } \| { type: "scroll", percent } \| { type: "exit" } \| { type: "time_on_page", seconds } \| { type: "inactivity", seconds } \| { type: "click", selector } \| { type: "event", name } \| { type: "manual" }.
`audience`	No	Who sees it: { who: all\|identified\|anonymous\|journey ("journey" only when a journey sends it), device: any\|desktop\|mobile, utm: {source, medium, campaign}, conditions: rules on contact fields }.
`priority`	No	Higher shows first.
`schedule`	No	{ start, end }: ISO dates or null.
`frequency`	No	{ repeat: once\|session\|days, days (for "days"), skipIfChatted: skip people who chatted in the last day }.
`productId`	No	One product, or null for every product.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 26, 2026

changedInput schema / properties / audience / properties / conditions / description

Previous value: -"Conditions on contact fields. mode \"all\" or \"any\"; each rule is { field, operator, value }. Fields: contact.name, contact.email, contact.consent (subscribed | unknown | unsubscribed), contact.email_status, contact.product_id, contact.created_at, contact.last_seen_at, contact.attributes.<field> (tags are contact.attributes.tags), contact.events.<event>. Operators: is, is_not, contains, not_contains, gt, lt, exists, missing, before, after (dates are ISO or now-7d)."New value: +"Conditions on contact fields. mode \"all\" or \"any\"; each rule is { field, operator, value }. Fields: contact.name, contact.email, contact.consent (subscribed | unknown | unsubscribed), contact.email_status, contact.product_id, contact.created_at, contact.last_seen_at, contact.attributes.<field> (tags are contact.attributes.tags), contact.events.<event>. Operators: is, is_not, contains, not_contains, gt, gte, lt, lte, between (value and value2), any_of and none_of (value is a list of strings), exists, missing, before, after (dates are ISO or now-7d)."

changed

Input schema / properties / audience / properties / conditions / properties / rules / items / properties / operator / enum

Previous value: -[
-  "is",
-  "is_not",
-  "contains",
-  "not_contains",
-  "gt",
-  "lt",
-  "exists",
-  "missing",
-  "before",
-  "after"
-]New value: +[
+  "is",
+  "is_not",
+  "contains",
+  "not_contains",
+  "gt",
+  "gte",
+  "lt",
+  "lte",
+  "between",
+  "any_of",
+  "none_of",
+  "exists",
+  "missing",
+  "before",
+  "after"
+]

addedInput schema / properties / audience / properties / conditions / properties / rules / items / properties / value / anyOf

Added value: +[
+  {
+    "type": [
+      "string",
+      "number",
+      "boolean"
+    ]
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

removedInput schema / properties / audience / properties / conditions / properties / rules / items / properties / value / type
```
Removed value: -[
-  "string",
-  "number",
-  "boolean"
-]
```
addedInput schema / properties / audience / properties / conditions / properties / rules / items / properties / value2
```
Added value: +{
+  "type": [
+    "string",
+    "number"
+  ]
+}
```

First observedOct 18, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already state readOnly=false, destructive=false, idempotent=false, so the safety profile is covered. The description adds the genuinely non-obvious behavioral fact: the message is inert ('Visitors see nothing') until published. It does not mention what is returned (no output schema) or duplicate-name behavior.

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

Conciseness5/5

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

Three short sentences, zero filler, with the draft-then-publish constraint front-loaded before the helper-tool mention. Every sentence carries information an agent would otherwise have to infer.

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?

For an 11-parameter, nested-object creation tool the description supplies the essential lifecycle context and the schema carries the deep structural detail. The remaining gap is the absence of any output schema and no hint of what a successful call yields (e.g., the created message's id), which the agent would need for a follow-up publish.

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 description coverage is 91% and the schema exhaustively documents kind-specific content shapes, trigger types, audience rules, frequency and schedule. The description adds no parameter detail, but the baseline for high-coverage schemas is 3 and the description's kind enumeration ('chat, pop-up or banner') mirrors the required discriminator helpfully. Slight bump above baseline, no more.

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 specific verb and resource ('Saves a new chat message, pop-up or banner as a draft') and immediately separates itself from siblings by naming publish_proactive_message and write_proactive_message_copy. An agent can tell this is the creation step of a draft-then-publish lifecycle 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.

Usage Guidelines4/5

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

Clearly conveys this is the drafting step and that publishing is a separate call, and points to write_proactive_message_copy as the content-generation alternative. It stops short of explicit exclusions (e.g., use update_proactive_message to edit an existing draft), so it is clear context rather than full routing guidance.

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

All HelpWell tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?