Skip to main content
Glama

Create draft automation

create_automation

Creates a comment-to-DM automation as a draft: when someone comments a keyword (or replies to a story, sends a DM or mentions the creator, see trigger), Pidgo replies (optionally in public) and sends them DMs. Write the messages in the creator's language and tone; keep them short and friendly. The draft does nothing until the creator switches it live in Pidgo, so share the open_in_pidgo link with them afterwards.

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": {
      "trigger": "<trigger>",
      "link": "<link>"
    },
    "name": "create_automation"
  }
}

Input Schema

NameRequiredDescriptionDefault
linkYesThe main DM.
openingNoOptional first DM with a button. When the person taps the button, the link message follows. Recommended: Instagram only lets Pidgo keep talking (follow gate, email, follow-up) after the person answers.
post_idNoInstagram media id from list_posts. Required when trigger is 'post'.
triggerYes'post': comments on one post (needs post_id). 'any': comments on any post. 'next': the next post the creator publishes. 'live': comments during an Instagram Live (no public reply). 'story': replies to any of the creator's stories. 'dm': a DM with the keyword. 'mention': someone mentions the creator in their story (no keywords). story, dm and mention start in the DMs: no public_reply and no opening; follow_gate, email_question and followup work without opening.
followupNoOptional reminder some hours later. Needs opening, except for story, dm and mention.
keywordsNoWords in a comment that start the automation, e.g. ['GUIDE']. Matching ignores case. Up to 20, each up to 30 characters.
any_keywordNoTrue to react to every comment, whatever it says. Then keywords are ignored.
follow_gateNoOptional: only send the link to people who follow the creator. Needs opening, except for story, dm and mention.
public_replyNoOptional public reply under the comment, e.g. 'Check your DMs!'. Max 300 characters.
email_questionNoOptional: ask for the person's email address before the link. Needs opening, except for story, dm and mention.
public_reply_variantsNoOptional: up to 3 other wordings of this message (max 300 characters each). Pidgo picks one at random every time, so the replies don't all look the same. Left out on update_automation, the current ones stay.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-idempotent write, and the description goes further by explaining that the artifact is a draft that 'does nothing until the creator switches it live in Pidgo' — a crucial safety fact that means creation has no public effect. It also tells the agent what to do afterward with the returned open_in_pidgo link and prescribes message tone/length, which is real behavioral context. It stops short of describing what happens on invalid trigger/optional-block combinations or whether repeated calls create duplicates (relevant given idempotentHint=false).

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?

Three sentences, front-loaded with purpose, then trigger scope, then draft semantics and the follow-up action. Little waste, though the parenthetical trigger recap partially duplicates the schema and the styling advice ('short and friendly') sits in the middle of behavioral facts.

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 an 11-parameter tool with three levels of nested objects and no output schema, the description supplies the essential lifecycle context (draft, not live) and the post-call step (share the link). The fully documented schema covers the field-level detail, so no critical instruction is missing, though a note on what the response contains and on the non-idempotent duplicate risk would make it complete.

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% for all 11 parameters including the nested link, opening, followup and follow_gate objects, so the description can only add beyond it. It does add the meaningful behavioral fact that the trigger choice restricts which optional blocks are valid ('story, dm and mention start in the DMs: no public_reply and no opening'), but that same constraint is also spelled out in the trigger enum description, so the net gain is modest. Baseline 3 applies when the schema carries this much detail.

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 description opens with a specific verb and resource ('Creates a comment-to-DM automation as a draft') and even enumerates the trigger surfaces it covers (comment keyword, story reply, DM, mention). It is clearly distinguishable from read-oriented siblings like get_automation, but it never names create vs. update_automation, which is the one sibling an agent could easily confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied through the trigger enumeration and the instruction to share the open_in_pidgo link afterwards, which tells the agent this is the entry point for a new automation. There is no explicit when-to-use/when-not statement and no routing to update_automation for editing an existing automation, so the agent must infer the create-vs-modify boundary.

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