Skip to main content
Glama

List auto-replies

list_auto_replies
Read-onlyIdempotent

The workspace's automatic-reply rules, oldest first — the first enabled rule that matches a comment or direct message answers it — each with its last-30-days numbers, plus what every account can do right now: comments (public replies, a private message to the commenter) and direct messages; missing_permissions are granted by reconnecting the account, or once the network approves Shager. What each network allows: Instagram: comments, public replies, private replies to the commenter, direct messages and files in private messages (an image, a video or a PDF); followers_only rules check who follows (works once Meta approves Shager; Instagram is in Meta's review). Facebook Pages: comments, public replies, private replies to the commenter, direct messages and files in private messages (an image, a video or a PDF); comments are read every 5 minutes until Meta delivers them instantly (works once Meta approves Shager's Page permissions; Facebook is in Meta's review). X: comments, public replies, private replies to the commenter and direct messages; billed to the workspace's monthly X limit (set_x_budget). YouTube: comments and public replies. LinkedIn company Pages: comments and public replies; Page comments are checked every 2 hours; LinkedIn has no messaging for Pages (works once LinkedIn approves Shager for company Pages). Not available: LinkedIn profiles, TikTok, Pinterest, Tumblr, Bluesky, Mastodon, Threads, Telegram, and Google reviews (Google requires the owner's consent for each reply).

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": "list_auto_replies"
  }
}

Input Schema

NameRequiredDescriptionDefault
workspace_idYesWorkspace id from list_workspaces

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered; the description adds genuine non-obvious behavior: first-enabled-match semantics, last-30-day metrics in the payload, per-network capability limits, polling cadence (5 minutes for Facebook, 2 hours for LinkedIn), and X billing against a monthly budget. Nothing contradicts the read-only annotations. It stops short of describing pagination or response shape, but with no output schema that is a minor gap.

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

Conciseness2/5

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

A single sprawling sentence followed by a per-network capability matrix that reads like product documentation rather than tool guidance; the actionable content (what the tool returns) is front-loaded but the rest is bulk. The Instagram/Facebook/X/YouTube/LinkedIn availability catalog and the list of unsupported networks consume most of the text without helping an agent decide or call correctly.

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 one-parameter read tool with no output schema, the definition covers ordering, evaluation semantics, permission failure handling and platform constraints — arguably more than needed. Returning accounts' capabilities is relevant context an agent would otherwise lack, even if the depth of the network matrix is excessive.

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?

Only one parameter, workspace_id, and the schema already documents it at 100% coverage with a pointer to list_workspaces. The description adds nothing about the identifier beyond what the schema says, so the baseline of 3 applies.

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 identifies the resource (the workspace's automatic-reply rules) and adds ordering ('oldest first') plus first-match evaluation semantics, which is more than a restatement of the name. It never contrasts itself with the sibling list_auto_reply_activity, so an agent has to infer why two 'list' tools exist; the purpose statement is also buried inside a long em-dash construction.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance, and no alternative is named (list_auto_reply_activity is an obvious candidate for the 'what happened recently' case). The permission-remediation sentence ('granted by reconnecting the account...') tells the agent what to do with a result, not when to call this tool.

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