Skip to main content
Glama
Sign In
SetLuca

SetLuca

Official
by setluca
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Generate a campaign plan

luca_campaigns_generate
Read-onlyIdempotent

Builds a fixed-rule campaign plan from a brief for review before you create and publish the draft. Requires lead source and, for comment campaigns, the comment keyword.

Instructions

Build a campaign plan from a brief with fixed rules, not an AI model. Nothing is created or published: create the draft from the plan, review it, and publish it yourself. A new brief has to say where leads come from: set body.source, or say it in body.prompt, for example a comment on a post or a DM. A comment campaign also has to name the word people comment in body.prompt, for example comment "GUIDE". If either is missing, Luca answers 400 and says what to add.

Luca operation: POST /api/campaigns/generate Required scopes: campaigns:read Required OAuth scope: luca:draft; data sensitivity: redacted Does not require idempotency. Use workspaceId or workspaceSlug to override the default workspace configured by environment.

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": {
      "body": "<body>"
    },
    "name": "luca_campaigns_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes
workspaceIdNoOptional Luca workspace id override.
workspaceSlugNoOptional Luca workspace slug override.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.2
    • removedInput schema / properties / idempotencyKey
      Removed value: -{
-  "description": "Stable key for safe retries. If omitted, the MCP server generates a unique key for this call.",
-  "minLength": 1,
-  "type": "string"
-}
  2. Changed2 schema fields changedv0.4.1
    • addedInput schema / properties / body / properties / existingGraph / properties / edges / items / properties / condition / additionalProperties
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "object"
+    },
+    {
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
    • addedInput schema / properties / body / properties / existingGraph / properties / nodes / items / properties / config / additionalProperties
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "object"
+    },
+    {
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
  3. First observedv0.4.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description is consistent with them while adding substantial context the annotations cannot carry: deterministic rule-based output rather than a model, explicit no-side-effect guarantee, required OAuth scope and data sensitivity, and precise failure behavior (400 with a message naming the missing field). That is exactly the beyond-annotation value this dimension rewards.

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-loaded and well ordered: what it does, what it does not do, hard validation rules, then operation metadata. Minor waste in the boilerplate 'Luca operation: POST /api/campaigns/generate' and two overlapping scope lines ('campaigns:read' and 'luca:draft') that could confuse an agent about which is binding.

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 a tool with a very deep nested schema and an output schema, the description covers the highest-risk gaps: the two validation rules that produce 400s, the no-write guarantee, and workspace override. It leaves the mode semantics unexplained (e.g. that improve_existing presumably needs existingGraph), which is the main remaining hole for such a complex payload.

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?

Adds meaning the schema cannot express: a cross-field constraint that body.source must be set or stated in body.prompt for new briefs, and that comment campaigns must name the trigger word in body.prompt. It also explains the workspaceId/workspaceSlug override role. It does not touch the many nested body fields (goal, mode, existingGraph, knowledge, qualification) which rely on the schema's 67% coverage.

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 (build a campaign plan) and immediately distinguishes the behavior from both AI generation and from sibling mutations: 'Nothing is created or published.' The agent can tell this apart from luca_campaigns_create and luca_campaigns_publish without opening any 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?

Clear context: use this to produce a plan, then 'create the draft from the plan, review it, and publish it yourself,' which sequences it ahead of the create/publish siblings. It also scopes the extra requirements to 'a new brief' and 'a comment campaign.' It stops short of naming the alternative tools explicitly, so the routing is implied rather than stated.

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