Skip to main content
Glama
kanjidoc
by kanjidoc

missive_create_draft

Create a draft message (email, SMS, WhatsApp, or custom channel) saved in Missive for manual review and sending. Appends to existing conversations or starts new ones.

Instructions

Creates a draft saved in Missive for manual review/sending — it does NOT send. Builds a draft email/SMS/WhatsApp/custom-channel message (in a new conversation, or appended to an existing one via conversation or references) that a human reviews and sends from the Missive app. The send-related parameters (send, send_at, auto_followup) are intentionally NOT available, so this tool can never transmit a message.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoHTML or text body of the message. Note: for paragraph spacing in Missive use <div>…</div> blocks separated by <div><br></div> rather than <p> tags.
teamNoTeam ID to link the draft's conversation to. Ignored if the conversation is already linked to a team.
closeNoClose the draft's conversation for everyone.
accountNoAccount ID for custom channel, Missive Live Chat, Messenger or Instagram drafts (Settings > API > Resource IDs).
subjectNoEmail subject, passed verbatim to the outgoing email. When replying, set to 'Re: [original subject]' so recipient clients thread it correctly.
add_usersNoUser IDs to grant access. Requires `organization` (explicit or MISSIVE_DEFAULT_ORGANIZATION).
cc_fieldsNoCC recipients (email only). Array of {address, name?} objects.
to_fieldsNoPrimary recipients. Array of recipient objects (shape depends on channel).
bcc_fieldsNoBCC recipients (email only). Array of {address, name?} objects.
force_teamNoWhen true, force the `team` even if the conversation is already in another team.
from_fieldNo
referencesNoMessage-ID/References header strings used to locate and append this draft to an existing conversation (chevrons optional). If none match, a new conversation is created.
attachmentsNoFiles to attach (up to 25). Each: base64_data (base64-encoded contents) and filename.
add_to_inboxNoWhen true, move the draft's conversation to Inbox for everyone with access.
conversationNoID of an existing Missive conversation to append this draft to (alternative to `references`).
organizationNoOrganization UUID. Scopes the conversation search and links new conversations to that organization. Defaults to MISSIVE_DEFAULT_ORGANIZATION. REQUIRED when `add_shared_labels` is used.
add_assigneesNoUser IDs to assign. Requires `organization` (explicit or MISSIVE_DEFAULT_ORGANIZATION).
remove_assigneesNoUser IDs to unassign. Requires `organization` (explicit or MISSIVE_DEFAULT_ORGANIZATION).
add_shared_labelsNoShared label IDs to apply to the draft's conversation. Requires `organization` (explicit or MISSIVE_DEFAULT_ORGANIZATION).
add_to_team_inboxNoWhen true, move the conversation to a team inbox. Requires `team`.
conversation_colorNoConversation color: a HEX code (e.g. '#000') or one of 'good', 'warning', 'danger'.
conversation_subjectNoSubject for the conversation in Missive (the internal conversation title).
remove_shared_labelsNoShared label IDs to remove from the draft's conversation.
quote_previous_messageNoWhen true, include a quoted copy of the conversation's last message in the draft. DANGER: when appending to an existing conversation (via `conversation`/`references`) this embeds the previous message's body and can leak sensitive content. Leave false unless you fully control and have visibility into the conversation. Defaults to false.
Behavior4/5

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

The description discloses that the tool never sends messages, warns about sensitive content leakage with quote_previous_message, and explains how conversations are created or appended. This adds value beyond the annotations (destructiveHint: false) by providing safety context. However, it does not cover all potential behaviors like error handling or rate limits.

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 a single, well-structured paragraph that front-loads the key point (does not send). It is concise given the tool's complexity (24 parameters) and includes essential warnings and usage notes without being verbose.

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?

The description covers key behaviors: draft creation, non-sending, channel support, new vs existing conversations, attachment limits, and important warnings. While it lacks output details (no output schema), it provides sufficient context for an AI agent to use the tool correctly.

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?

With 96% schema coverage, the schema already describes most parameters. The description adds meaningful context, such as the warning for quote_previous_message and the explanation of references and conversation. This supplements the schema without redundancy.

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 clearly states it creates a draft for manual review/sending and explicitly says it does NOT send. It distinguishes from sending tools by noting send-related parameters are unavailable, and it supports multiple channels, making the purpose specific and unambiguous.

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 implies usage for drafts that require human review, and explicitly states that it cannot transmit messages. However, it does not directly compare to sibling tools like missive_create_message, which sends messages, leaving some ambiguity about when to use each. A brief contrast would improve clarity.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kanjidoc/missive-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server