Skip to main content
Glama

Craft message

campaignstack_craft_message

Draft one outbound message without sending anything. Select channel linkedin/email and kind first_touch, connection_note, comment, comment_reply, followup, or meeting_followup. Returns sent:false; callers must read the draft back and use a separate send/action tool only after explicit approval. It never books a meeting for you: when a follow-up finds the lead accepted a time offered earlier, schedulingAcceptance names it (booked:false) for a person to book.

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": {
      "channel": "<channel>",
      "kind": "<kind>"
    },
    "name": "campaignstack_craft_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
leadIdNo
channelYesDraft channel. LinkedIn drafts do not send; email drafts do not send.
postUrlNoFor first_touch, pair with postContent for a post authored by the lead. Required for comment drafts: the target LinkedIn post URL containing its activity id, or its urn:li:activity URN. Posts older than five days are skipped before crafting.
newEndAtNo
postDateNoPost publication time in Unix milliseconds, when known.
templateNo
accountIdNoLinkedIn account that will send the draft: names the speaker and picks the voice on every LinkedIn kind. For a LinkedIn follow-up it also reads the thread, and defaults to the workspace's only LinkedIn account ready to use; with several, the error lists them so you can ask the person.
meetingIdNoRequired for kind=meeting_followup.
campaignIdNo
newStartAtNo
workflowIdNo
commentTextNo
meetingKindNo
postContentNoFor first_touch, supply the lead-authored post text with postUrl so the opener can cite it and review retains the evidence.
workspaceIdNoWorkspace ID. Omit it when this connection reaches one workspace: a workspace key (cs_) is bound to its own, and a user key (csu_) or connected app whose person belongs to exactly one workspace defaults to that one. Required only when the person belongs to several; the error then lists them, and campaignstack_whoami reports them too.
instructionsNo
conversationMessagesNo

Output Schema

NameRequiredDescriptionDefault
okNo
resultsNo
workspaceIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / postContent / description
      Added value: +"For first_touch, supply the lead-authored post text with postUrl so the opener can cite it and review retains the evidence."
    • addedInput schema / properties / postDate
      Added value: +{
      +  "description": "Post publication time in Unix milliseconds, when known.",
      +  "type": "number"
      +}
    • changedInput schema / properties / postUrl / description
      Previous value: -"Required for comment drafts: the target LinkedIn post URL containing its activity id, or its urn:li:activity URN. Posts older than five days are skipped before crafting."New value: +"For first_touch, pair with postContent for a post authored by the lead. Required for comment drafts: the target LinkedIn post URL containing its activity id, or its urn:li:activity URN. Posts older than five days are skipped before crafting."
  2. Changed1 schema field changed
    • addedInput schema / properties / postUrl
      Added value: +{
      +  "description": "Required for comment drafts: the target LinkedIn post URL containing its activity id, or its urn:li:activity URN. Posts older than five days are skipped before crafting.",
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • changedInput schema / properties / accountId / description
      Previous value: -"LinkedIn account that will send the draft: names the speaker and picks the voice on every LinkedIn kind. Required for a LinkedIn follow-up, where it also reads the thread."New value: +"LinkedIn account that will send the draft: names the speaker and picks the voice on every LinkedIn kind. For a LinkedIn follow-up it also reads the thread, and defaults to the workspace's only LinkedIn account ready to use; with several, the error lists them so you can ask the person."
  4. Changed1 schema field changed
    • changedInput schema / properties / accountId / description
      Previous value: -"LinkedIn account for follow-up thread context."New value: +"LinkedIn account that will send the draft: names the speaker and picks the voice on every LinkedIn kind. Required for a LinkedIn follow-up, where it also reads the thread."
  5. Changed1 schema field changed
    • changedInput schema / properties / workspaceId / description
      Previous value: -"Workspace ID. REQUIRED for a user key (csu_), which spans every workspace you belong to; omitted for a workspace key (cs_), which is bound to one and ignores this argument. campaignstack_whoami reports which kind of key you are holding and, for a user key, the workspaces it can reach."New value: +"Workspace ID. Omit it when this connection reaches one workspace: a workspace key (cs_) is bound to its own, and a user key (csu_) or connected app whose person belongs to exactly one workspace defaults to that one. Required only when the person belongs to several; the error then lists them, and campaignstack_whoami reports them too."
  6. Changed22 schema fields changed
    • addedInput schema / properties / accountId
      Added value: +{
      +  "description": "LinkedIn account for follow-up thread context.",
      +  "type": "string"
      +}
    • addedInput schema / properties / channel
      Added value: +{
      +  "description": "Draft channel. LinkedIn drafts do not send; email drafts do not send.",
      +  "enum": [
      +    "linkedin",
      +    "email"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / commentText
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / conversationMessages
      Added value: +{
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "sender": {
      +        "enum": [
      +          "self",
      +          "lead"
      +        ],
      +        "type": "string"
      +      },
      +      "text": {
      +        "minLength": 1,
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "sender",
      +      "text"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 100,
      +  "type": "array"
      +}
    • addedInput schema / properties / instructions / maxLength
      Added value: +4000
    • addedInput schema / properties / kind
      Added value: +{
      +  "enum": [
      +    "first_touch",
      +    "connection_note",
      +    "comment",
      +    "comment_reply",
      +    "followup",
      +    "meeting_followup"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / properties / leadId / minLength
      Removed value: -1
    • addedInput schema / properties / meetingId
      Added value: +{
      +  "description": "Required for kind=meeting_followup.",
      +  "type": "string"
      +}
    • addedInput schema / properties / meetingKind
      Added value: +{
      +  "enum": [
      +    "reschedule",
      +    "no_show",
      +    "cancelled"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / properties / messageTemplate
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / properties / newEndAt
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / newStartAt
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / postContent
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / template
      Added value: +{
      +  "maxLength": 4000,
      +  "type": "string"
      +}
    • removedInput schema / properties / workflowId / description
      Removed value: -"Workflow the craft belongs to. Used to resolve signal-agent playbooks. Injected automatically for runner agents."
    • changedInput schema / required
      Previous value: -[
      -  "leadId"
      -]New value: +[
      +  "channel",
      +  "kind"
      +]
    • removedOutput schema / properties / messageText
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "anyOf": [
      -        {
      -          "not": {}
      -        },
      -        {
      -          "type": "string"
      -        }
      -      ]
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ]
      -}
    • removedOutput schema / properties / needsHumanReview
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "anyOf": [
      -        {
      -          "not": {}
      -        },
      -        {
      -          "type": "boolean"
      -        }
      -      ]
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ]
      -}
    • addedOutput schema / properties / ok
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / results
      Added value: +{
      +  "items": {},
      +  "type": "array"
      +}
    • removedOutput schema / properties / reviewReason
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "anyOf": [
      -        {
      -          "not": {}
      -        },
      -        {
      -          "type": [
      -            "string",
      -            "null"
      -          ]
      -        }
      -      ]
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ]
      -}
    • addedOutput schema / properties / workspaceId
      Added value: +{
      +  "type": "string"
      +}
  7. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": true,
      +  "properties": {
      +    "messageText": {
      +      "anyOf": [
      +        {
      +          "anyOf": [
      +            {
      +              "not": {}
      +            },
      +            {
      +              "type": "string"
      +            }
      +          ]
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "needsHumanReview": {
      +      "anyOf": [
      +        {
      +          "anyOf": [
      +            {
      +              "not": {}
      +            },
      +            {
      +              "type": "boolean"
      +            }
      +          ]
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "reviewReason": {
      +      "anyOf": [
      +        {
      +          "anyOf": [
      +            {
      +              "not": {}
      +            },
      +            {
      +              "type": [
      +                "string",
      +                "null"
      +              ]
      +            }
      +          ]
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
  8. Changed9 schema fields changed
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / campaignId
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / instructions
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / leadId
      Added value: +{
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / messageTemplate
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / workflowId
      Added value: +{
      +  "description": "Workflow the craft belongs to. Used to resolve signal-agent playbooks. Injected automatically for runner agents.",
      +  "type": "string"
      +}
    • addedInput schema / properties / workspaceId
      Added value: +{
      +  "description": "Workspace ID. REQUIRED for a user key (csu_), which spans every workspace you belong to; omitted for a workspace key (cs_), which is bound to one and ignores this argument. campaignstack_whoami reports which kind of key you are holding and, for a user key, the workspaces it can reach.",
      +  "type": "string"
      +}
    • addedInput schema / required
      Added value: +[
      +  "leadId"
      +]
  9. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations (which only say not read-only, not destructive, not idempotent), the description discloses that nothing is sent, that the response carries sent:false, that a read-back step is required, and that schedulingAcceptance surfaces an accepted time with booked:false for human booking. That is substantive behavioral context an agent could not infer from the structured fields.

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?

Content is front-loaded: draft-only behavior first, selection inputs second, then the approval and scheduling caveats. Sentences are information-dense with little padding, though the final sentence about schedulingAcceptance is syntactically dense and takes a second pass to parse.

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

Completeness3/5

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

An output schema exists, so return values need not be spelled out, and the description covers the critical safety and workflow story. However, for an 18-parameter drafting tool with 39% schema coverage, the absence of any guidance on the many optional scoping/timing/thread parameters leaves the definition only partially complete.

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

Parameters2/5

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

Schema coverage is only 39% across 18 parameters, so the description carries a heavy burden, yet it only expands on channel and kind and says nothing about leadId, campaignId, workflowId, template, instructions, commentText, meetingKind, the newStartAt/newEndAt pair, or conversationMessages. The one useful hint is that meeting_followup relates to schedulingAcceptance, but most undocumented parameters remain unexplained in both places.

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 names a specific verb and resource ('Draft one outbound message') and immediately bounds scope ('without sending anything'), which cleanly separates it from the send/action siblings. It also enumerates the channel and kind values an agent must pick, so the tool's identity is unambiguous before 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 Guidelines5/5

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

It states the required selection inputs (channel and kind) and gives an explicit workflow: read the draft back, then use 'a separate send/action tool only after explicit approval.' It also pre-empts a wrong expectation by saying the tool never books a meeting and that a person must act on schedulingAcceptance, which is exactly the when/when-not guidance an agent needs.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources