honeybook-mcp

Overview Schema Source Related Servers Discussions Admin

send_message

Destructive

Sends messages or threaded replies to vendors and workspace members through the HoneyBook portal, with confirmation before delivery.

Instructions

Send a message to the vendor (and the other members of the workspace) through the HoneyBook portal, exactly as the Activity tab composer does. HoneyBook emails it to every recipient. Pass reply_to_message_id to reply in-thread (the subject is inherited). Asks the user to confirm first: a confirmation prompt where the client supports one; otherwise the first call returns a preview and a confirmToken, and only a repeat call with that token proceeds (see MCP_CONFIRM_MODE). If HoneyBook has not finished sending within about a minute the result has status "pending" and a task_id; if it did not answer the send request at all the status is "unknown". Either way the message may still be delivered, so check list_messages before resending.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "workspace_id": "<workspace_id>",
      "body": "<body>"
    },
    "name": "send_message"
  }
}

Input Schema

Name	Required	Description
`body`	Yes	Message text, written as `format` says. With no format, plain text is sent as-is (line breaks preserved) and a body using HTML tags is read as HTML.
`format`	No	"text" (sent as typed), "markdown" (bold, _italic_, lists, [links](https://…), `code`, # headings, > quotes — sent as formatted HTML, and cheaper to write than HTML) or "html" (simple formatting kept: p, br, b, i, a href, lists, tables; other tags shown as text, attributes other than an http(s)/mailto link dropped). Omitted: "html" if the body uses an HTML tag, else "text".
`origin`	No	Portal origin (e.g. https://<vendor>.hbportal.co). Optional when only one session is active.
`subject`	No	Required for a new message; optional on a reply.
`confirmToken`	No	ONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 "confirmation-required" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.
`workspace_id`	Yes	The workspace _id (from list_projects, or .workspace._id on any workspace_file).
`reply_to_message_id`	No	A message _id from list_messages to reply to.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.4.0Nov 12, 2026

changedInput schema / properties / body / description

Previous value: -"Message text. Plain text is sent as-is (line breaks preserved). Simple HTML formatting (p, br, b, i, a href, lists, tables) is kept; other tags are shown as text and attributes other than an http(s)/mailto link are dropped."New value: +"Message text, written as `format` says. With no format, plain text is sent as-is (line breaks preserved) and a body using HTML tags is read as HTML."

addedInput schema / properties / format

Added value: +{
+  "description": "\"text\" (sent as typed), \"markdown\" (**bold**, _italic_, lists, [links](https://…), `code`, # headings, > quotes — sent as formatted HTML, and cheaper to write than HTML) or \"html\" (simple formatting kept: p, br, b, i, a href, lists, tables; other tags shown as text, attributes other than an http(s)/mailto link dropped). Omitted: \"html\" if the body uses an HTML tag, else \"text\".",
+  "enum": [
+    "text",
+    "markdown",
+    "html"
+  ],
+  "type": "string"
+}

Changed1 schema field changedv1.2.7Oct 17, 2026

changedInput schema / properties / body / description

Previous value: -"Message text. Plain text is sent as-is (line breaks preserved); HTML is passed through."New value: +"Message text. Plain text is sent as-is (line breaks preserved). Simple HTML formatting (p, br, b, i, a href, lists, tables) is kept; other tags are shown as text and attributes other than an http(s)/mailto link are dropped."

Changed2 schema fields changedv1.2.1Sep 25, 2026

removedInput schema / properties / confirm

Removed value: -{
-  "description": "Must be true to actually send. Without it the tool returns a preview of what would go out.",
-  "type": "boolean"
-}

addedInput schema / properties / confirmToken

Added value: +{
+  "description": "ONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 \"confirmation-required\" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.",
+  "type": "string"
+}

Changed1 schema field changedv1.0.0Sep 19, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Addedv0.9.0Sep 3, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already flag a non-read-only, destructive, non-idempotent, open-world write; the description adds substantial context beyond them: real email delivery to every recipient, a mandatory user confirmation step with two fallback modes, and the pending/unknown statuses with the warning that the message may still be delivered. That last point directly operationalizes idempotentHint=false and destructiveHint=true.

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?

Front-loads the core action and recipient set, then layers in reply behavior, confirmation, and failure states in a logical order. It is dense with parentheticals and long sentences, but nearly every clause carries operational information, so little is wasted.

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

Completeness5/5

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

For a 7-parameter mutation tool with no output schema, the description supplies what an agent needs: confirmation flow and confirmToken rules, reply semantics, the pending/unknown states and how to verify delivery. Nothing required to invoke it correctly is missing.

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 description coverage is 100%, including detailed enum semantics for format and inferencing rules for an omitted format, so the schema does the heavy lifting and the baseline is 3. The description adds only one extra fact beyond the schema: that a reply inherits the subject from the replied-to 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 specific verb and resource (send a message) plus exactly who receives it: the vendor and other workspace members via the HoneyBook portal, emailed to every recipient. This is clearly distinguishable from the read-oriented siblings such as list_messages and get_message.

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 concrete routing guidance: pass reply_to_message_id to reply in-thread, and check list_messages before resending after a 'pending' or 'unknown' result. It explains the confirmation prerequisite in detail but does not contrast itself with other outbound paths (notes, flows, attachments), so a full 5 is not earned.

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