Skip to main content
Glama

Set cloud patrol

set_cloud_patrol
DestructiveIdempotent

Creates or updates an account's cloud patrol: keywords (1 to 10; a "#tag" entry searches a topic tag), reply persona, daily_cap (1 to 50 on free and trial, up to 80 on paid plans, up to 150 with a haixun add-on), enabled, and review_before_reply. When patrol is on, the account replies to relevant fresh Threads posts through the official API every 15 minutes, one patrol point per delivered reply; with review_before_reply:true every drafted reply waits in list_pending_replies instead of going out. Turning patrol on, or changing a patrol that is already on, needs the patrol permission, which is not granted to directory connections: the owner does it in MindThread. Applies when the user wants to stop patrol or tune its keywords, persona and cap while it is off.

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": {
      "account_id": "<account_id>"
    },
    "name": "set_cloud_patrol"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo"reply" (default): AI drafts and posts replies. "discover": only list matching posts for you to read; no AI, nothing posted
enabledNoStart / stop
personaNoReply persona
keywordsNo1-10 entries; "#tag" = topic-tag search
daily_capNoreply: 1-50 free/trial, up to 80 paid, up to 150 with add-on; discover: 1 to plan daily haixun points (default)
reply_maxNoMax characters per reply, 20-200, or null for the language default. A persona asking for a length is followed up to this limit
account_idYesAccount id
reply_modeNo"ai" (default): AI writes each reply in the persona. "rotate": post your fixed replies in order, word for word, starting over after the last (AI still decides which posts to reply to). "consume": like rotate but each reply is used once; patrol stops for the account when all are used. Fixed replies come from rotate_replies or the imported library (import_cloud_patrol_replies)
rotate_repliesNo1-10 fixed replies used in order when reply_mode is "rotate"; each within the account reply length limit; changing them restarts from the first
review_before_replyNoHold drafts for approval

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / reply_max
      Added value: +{
      +  "description": "Max characters per reply, 20-200, or null for the language default. A persona asking for a length is followed up to this limit",
      +  "maximum": 200,
      +  "minimum": 20,
      +  "type": "integer"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / reply_mode / description
      Previous value: -"\"ai\" (default): AI writes each reply in the persona. \"rotate\": post your fixed rotate_replies in order, word for word (AI still decides which posts to reply to)"New value: +"\"ai\" (default): AI writes each reply in the persona. \"rotate\": post your fixed replies in order, word for word, starting over after the last (AI still decides which posts to reply to). \"consume\": like rotate but each reply is used once; patrol stops for the account when all are used. Fixed replies come from rotate_replies or the imported library (import_cloud_patrol_replies)"
    • changedInput schema / properties / reply_mode / enum
      Previous value: -[
      -  "ai",
      -  "rotate"
      -]New value: +[
      +  "ai",
      +  "rotate",
      +  "consume"
      +]
  3. Changed2 schema fields changed
    • addedInput schema / properties / reply_mode
      Added value: +{
      +  "description": "\"ai\" (default): AI writes each reply in the persona. \"rotate\": post your fixed rotate_replies in order, word for word (AI still decides which posts to reply to)",
      +  "enum": [
      +    "ai",
      +    "rotate"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / rotate_replies
      Added value: +{
      +  "description": "1-10 fixed replies used in order when reply_mode is \"rotate\"; each within the account reply length limit; changing them restarts from the first",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  4. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Against annotations that only say destructive/idempotent/open-world, the description supplies real operational context: a 15-minute reply cadence, one patrol point consumed per delivered reply, and the review_before_reply branch that diverts drafts to list_pending_replies instead of posting. It does not explain the destructive aspect - e.g. that omitting a field may clear it, or that changing rotate replies restarts from the first - so an agent must infer why destructiveHint is 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-loaded correctly: the mutation and its fields come first, operational cadence and cost second, permissions last. The prose is dense but nearly every clause carries information; the only weak spot is the ambiguous trailing sentence, which costs clarity without adding much.

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 10-parameter, no-output-schema config mutation it covers the essentials an agent needs: cost model, cadence, approval flow and the permission blocker. The remaining gap is update semantics - whether this is a full replace or a partial patch, and what stopping patrol does to existing configuration - which matters given destructiveHint=true and idempotentHint=true.

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%, so every parameter including mode, reply_mode, reply_max and rotate_replies is already fully documented. The description only restates a subset (keywords 1-10, daily_cap plan tiers, enabled, review_before_reply) and adds no merge-vs-replace semantics - whether unspecified fields are preserved or wiped on update is left open.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause names a specific verb pair and resource ("Creates or updates an account's cloud patrol") and immediately enumerates the configurable surface (keywords, persona, daily_cap, enabled, review_before_reply). It routes one interaction to a sibling by naming list_pending_replies as where held drafts land, but never contrasts itself with get_cloud_patrol or cloud_patrol_stats, so differentiation is partial rather than explicit.

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?

It states a hard precondition absent from the schema: turning patrol on or changing an already-on patrol needs the patrol permission, which directory connections lack, so the owner must do it in MindThread. That is a genuine when-not-to-call signal. The closing sentence ("Applies when the user wants to stop patrol or tune its keywords, persona and cap while it is off") is muddled and slightly at odds with the preceding permission rule, keeping it short of a 5.

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.