Skip to main content
Glama

Create an auto-reply

create_auto_reply
Destructive

Adds a rule that answers comments or direct messages automatically, on the person's behalf, from now on (never older comments). trigger COMMENT: when someone comments (optionally only with one of keywords, whole words, any case; only on post_ids; only on channel_ids), post one of public_replies (picked at random) under the comment and/or send message (+ link_url as a tracked short link) privately to the commenter, once per comment within 7 days. trigger MESSAGE: when someone sends a direct message (optionally with a keyword), answer with message within 24 hours. once_per_person (default true) answers each person once per rule per 30 days. At most 120 replies per account per hour. followers_only (COMMENT, Instagram): "comment a word, follow, get the link": the private reply asks them to follow and tap follow_button; the tap lets Shager check with Instagram, and only followers get message + link_url. attachment_media_id (Instagram, Facebook): also send a file privately (a guide, a price list, a coupon image); on comments it goes out after they tap follow_button, since the first private reply can only be text. It is saved paused (enabled=false) unless you pass enabled=true. An enabled rule answers real people with no one checking each answer, so enabled=true first needs your human's OK: the call answers needs_confirmation with confirm_url, where they read every text; after they approve, make the same call again. (Not available in an unclaimed sandbox.)

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>",
      "name": "<name>",
      "trigger": "<trigger>"
    },
    "name": "create_auto_reply"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesA short name the person will recognize, e.g. "Link in DM"
enabledNofalse (the default): the rule is saved paused. true: it starts answering real people, so it first needs your human's OK in Shager (needs_confirmation with confirm_url, then the same call again)
messageNoThe private message (to the commenter, or the answer to a direct message)
triggerYesCOMMENT: someone comments on a post. MESSAGE: someone sends a direct message
keywordsNoWhole words or phrases, any case; empty = every comment or message
link_urlNoAdded at the end of the private message as a tracked short link
post_idsNoCOMMENT only: only comments on these Shager posts; empty = every post
channel_idsNoOnly these accounts; empty = every account that supports the trigger
workspace_idYesWorkspace id from list_workspaces
follow_buttonNofollowers_only: the button's text, up to 20 characters, e.g. "I'm following" (required with followers_only)
follow_promptNofollowers_only: the private reply asking them to follow and tap the button (required with followers_only)
followers_onlyNoCOMMENT only, Instagram only: the private reply is `follow_prompt` with a `follow_button`; when the person taps it, Shager asks Instagram whether they follow and sends `message` + `link_url` only to followers (others get `follow_reminder` with the button, up to 5 times). Accounts without follower_check in list_auto_replies skip these comments
public_repliesNoCOMMENT only: public answers under the comment, one picked at random
follow_reminderNofollowers_only: sent with the button again when they tap it without following yet; empty = follow_prompt again
idempotency_keyNoAny unique string you choose (REST: the Idempotency-Key header works too). Retrying with the same key and body returns the first result instead of creating a second one. Kept 24 hours.
once_per_personNoAnswer each person once per rule (30 days)
confirmation_tokenNoThe confirmation_token from needs_confirmation. The call goes through only after your human approved this exact action at confirm_url.
attachment_media_idNoInstagram and Facebook: a file sent privately after `message`: an image (up to 8 MB), a video or a PDF (up to 25 MB) from this workspace's media (create_media_upload or upload_media_from_url first). On COMMENT rules the networks allow only text in the first private reply, so the private reply is `follow_prompt` with a `follow_button` and the file goes out when they tap it (with followers_only, only to followers). Accounts without `files` in list_auto_replies send the message without it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / attachment_media_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 64,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Instagram and Facebook: a file sent privately after `message`: an image (up to 8 MB), a video or a PDF (up to 25 MB) from this workspace's media (create_media_upload or upload_media_from_url first). On COMMENT rules the networks allow only text in the first private reply, so the private reply is `follow_prompt` with a `follow_button` and the file goes out when they tap it (with followers_only, only to followers). Accounts without `files` in list_auto_replies send the message without it"
      +}
  2. Changed3 schema fields changed
    • addedInput schema / properties / confirmation_token
      Added value: +{
      +  "description": "The confirmation_token from needs_confirmation. The call goes through only after your human approved this exact action at confirm_url.",
      +  "maxLength": 100,
      +  "type": "string"
      +}
    • changedInput schema / properties / enabled / default
      Previous value: -trueNew value: +false
    • addedInput schema / properties / enabled / description
      Added value: +"false (the default): the rule is saved paused. true: it starts answering real people, so it first needs your human's OK in Shager (needs_confirmation with confirm_url, then the same call again)"
  3. Changed4 schema fields changed
    • addedInput schema / properties / follow_button
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 20,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "followers_only: the button's text, up to 20 characters, e.g. \"I'm following\" (required with followers_only)"
      +}
    • addedInput schema / properties / follow_prompt
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 640,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "followers_only: the private reply asking them to follow and tap the button (required with followers_only)"
      +}
    • addedInput schema / properties / follow_reminder
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 640,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "followers_only: sent with the button again when they tap it without following yet; empty = follow_prompt again"
      +}
    • addedInput schema / properties / followers_only
      Added value: +{
      +  "default": false,
      +  "description": "COMMENT only, Instagram only: the private reply is `follow_prompt` with a `follow_button`; when the person taps it, Shager asks Instagram whether they follow and sends `message` + `link_url` only to followers (others get `follow_reminder` with the button, up to 5 times). Accounts without follower_check in list_auto_replies skip these comments",
      +  "type": "boolean"
      +}
  4. First observed

TDQS

A4.1/5.0
Behavior3/5

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

The description adds a great deal beyond the annotations: hourly cap of 120 replies, 7-day once-per-comment window, 24-hour DM window, 30-day once_per_person, paused-by-default, the two-step confirmation handshake, and the send ordering for attachments. However, the annotations declare destructiveHint=true and the description's only destructive framing is the 'answers real people' warning; it never clarifies irreversibility (that delete_auto_reply is needed) which is the main risk an agent should know before creating a live rule.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Nearly every clause carries real information, and the core behavior is front-loaded in the first sentence. But it is delivered as one enormous run-on paragraph with stacked parentheticals, so an agent must parse a dense block rather than scan headers or bullets for the trigger-specific rules.

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 an 18-parameter mutation tool with no output schema, the description covers what's needed: prerequisites (create_media_upload or upload_media_from_url first, capability flags via list_auto_replies, workspace id from list_workspaces), rate limits, the confirmation round-trip, and per-trigger applicability constraints. Little an agent needs in order to call it correctly is missing.

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?

Schema coverage is 100%, so the baseline is 3; the description earns above that by documenting cross-parameter dependencies the schema only states locally, e.g. that follow_button/follow_prompt are required together with followers_only, that the private reply must be text first on COMMENT rules so attachment_media_id is deferred to the follow tap, and that public_replies is chosen at random.

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 opening sentence states a specific verb and resource ('Adds a rule that answers comments or direct messages automatically') plus the crucial scope constraint 'from now on (never older comments)'. The COMMENT vs MESSAGE trigger split immediately tells an agent which of the two automation shapes it is creating, which is not derivable from the name alone.

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?

Usage conditions are unusually explicit: the rule is saved paused unless enabled=true, enabling requires human approval via needs_confirmation/confirm_url and a repeat call, and the tool is unavailable in an unclaimed sandbox. It does not name update_auto_reply or list_auto_replies as alternatives for editing or capability checks, so sibling routing is left implicit rather than stated.

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