Skip to main content
Glama

get_automation_activity

Read-only

The activity of a comment-to-DM automation, newest first: one row per comment or message it acted on, with the DM sent, an answer that waits in the queue (queued: the send cap is full or the platform asked to wait; it goes out as soon as there is room), a skip and its reason (already got the DM, limit reached, comment older than 7 days, the send cap stayed full for a day on Instagram and Facebook or an hour on X, the person does not accept DMs from the X account, the person replied STOP earlier, the automation was paused while the answer waited), a person who replied STOP on X (opted_out: no automatic DMs to them from that X account again, in any workspace or automation), or a failure with the platform's error. With Follow first (Instagram) a row can be waiting (asked to follow, no link yet: it shows whether the person tapped the button and how often), a skip can say the person was already asked to follow, and a sent row says whether the person followed after the ask, already followed, or got the link without a check. With a follow-up (Instagram and Facebook) a row can be waiting for the tap (the tap step on an Instagram comment: no link until the person taps), and each sent row says where its follow-up is: due at a time, sent, or kept back with the reason (no tap or message from the person in Meta's 24-hour window, the person said stop, a team member answered by hand, the automation or the follow-up was switched off). On the Facebook Page the person shows by name (Facebook has no @handle). Use it to answer 'how many people got the DM' or 'why did this person not get it'.

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": {
      "automation_id": "<automation_id>"
    },
    "name": "get_automation_activity"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoRows per page (default 25, max 100).
offsetNoRows to skip (for the next page).
outcomeNoOnly rows with this outcome.
automation_idYesThe automation id (from list_automations).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / outcome / enum
      Previous value: -[
      -  "sent",
      -  "skipped",
      -  "failed",
      -  "pending",
      -  "queued",
      -  "opted_out"
      -]New value: +[
      +  "sent",
      +  "skipped",
      +  "failed",
      +  "pending",
      +  "queued",
      +  "opted_out",
      +  "waiting"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / outcome / enum
      Previous value: -[
      -  "sent",
      -  "skipped",
      -  "failed",
      -  "pending"
      -]New value: +[
      +  "sent",
      +  "skipped",
      +  "failed",
      +  "pending",
      +  "queued",
      +  "opted_out"
      +]
  3. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds real value beyond that: it discloses the ordering guarantee (newest first), and defines what each outcome means (queued means the send cap is full and it will go out when there's room; opted_out means no automatic DMs to that person from that X account in any workspace). It doesn't discuss pagination behavior or response envelope, but that's minor for a read tool.

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?

The core statement is front-loaded correctly ('The activity of a comment-to-DM automation, newest first'), but the body is an extremely long run-on with deeply nested parentheticals that makes it hard to scan. Almost all content is relevant, so it isn't padding, but the packing into one sentence costs readability.

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?

Read tool with annotations, no output schema, and full schema coverage — so the description's main remaining job is explaining what a row represents, and it does so exhaustively (comment vs. message, DM sent, queue state, skip reasons, opt-out scope, platform-specific behavior for Follow first and follow-ups, Facebook Page name display). It omits nothing an agent would need to interpret results or call the tool correctly.

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 limit/offset/automation_id are already documented and the baseline would be 3. The description earns above baseline by explaining the semantic meaning of nearly every value in the outcome enum (sent, skipped, queued, pending, opted_out, waiting, failed) with the conditions that produce them, which helps an agent choose a filter value. It never explicitly ties those meanings back to the outcome filter parameter, which is why it isn't a 5.

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?

Opens with a specific verb+resource: 'The activity of a comment-to-DM automation, newest first: one row per comment or message it acted on.' An agent can tell this is the per-action log, distinct from configuration retrieval, and it doesn't rely on the name alone. It never explicitly names a sibling like get_automation to contrast with, which keeps it from a 5.

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?

Closes with concrete use cases: 'answer how many people got the DM or why did this person not get it.' That gives clear triggering contexts. It stops short of explicit when-not-to-use guidance or naming an alternative tool for configuration vs. activity, so it's not 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.

Resources