Skip to main content
Glama

Comments on a published post

list_comments

Reads the comments (newest first, each with its replies) on a post Shager published, on one account. YouTube: comments and their replies; reply; hide others' comments; delete only the account's own. Facebook Pages: comments and their replies, once the Page granted Meta's comment permissions (pages_read_user_content, pages_manage_engagement; a Page connected before Shager asked for them needs a reconnect); reply; hide others' comments; delete any comment on the account's post. Instagram: comments and their replies; reply; hide others' comments; delete any comment on the account's post. X: replies from the last 7 days, up to 20 a read; every read, reply and delete is billed to the workspace's monthly X limit; reply; no hiding; delete only the account's own. LinkedIn company Pages: comments and their replies, answered as the Page; commenters come without names; reply; no hiding; delete only the account's own. Bluesky: replies two levels deep; reply; no hiding; delete only the account's own. Mastodon: replies, including followers-only ones the account can see, answered with the same visibility; reply; no hiding; delete only the account's own. Threads: the whole conversation under the post, once the profile granted threads_read_replies; reply; hide others' comments; no deleting. LinkedIn profiles, TikTok and Pinterest don't let apps manage comments; Telegram channel comments and Tumblr replies aren't offered; Google Business Profile reviews are read with list_reviews. Each comment carries can_hide and can_delete for this account. Read live from the network, never stored. Use it to answer questions, spot spam, or draft replies for a human to approve.

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>",
      "post_id": "<post_id>",
      "channel_id": "<channel_id>"
    },
    "name": "list_comments"
  }
}

Input Schema

NameRequiredDescriptionDefault
post_idYes
channel_idYesThe account the post went to (destinations[].channel_id in get_post)
workspace_idYesWorkspace id from list_workspaces

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations: permission prerequisites and the reconnect requirement for Meta (pages_read_user_content, pages_manage_engagement, threads_read_replies), hard limits (X: 7 days, 20 per read), billing impact (every X read/reply/delete counts against the monthly limit), data freshness (read live, never stored), and per-comment can_hide/can_delete flags. Annotations only give readOnlyHint=false and openWorldHint=true, so this description carries and supplies the real behavioral burden.

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?

Purpose and ordering are front-loaded in the first sentence, and the platform matrix is scannable despite repeated "reply; no hiding; delete only the account's own" phrasing. The main structural weakness is that the when-to-use sentence, which is high-value, is buried at the very end of a ~230-word block.

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?

With no output schema, the description still explains what comes back (comments plus replies, can_hide/can_delete per comment) and covers the platform-specific preconditions that determine whether the call succeeds. Nothing an agent needs to call this read correctly appears to be missing.

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 coverage is 67%: workspace_id and channel_id are already documented in the schema (channel_id even points at destinations[].channel_id in get_post), and post_id is undocumented in both places. The description adds only loose context ("on a post ... on one account") without explaining post_id format or scoping, so this sits at the baseline for moderate coverage.

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?

States a specific verb and resource ("Reads the comments ... on a post ... on one account") and immediately fixes ordering (newest first) and shape (each with its replies). It also explicitly rules out adjacent resources, e.g. Google Business Profile reviews go to list_reviews, so an agent can distinguish it from list_reviews and get_post without opening a schema.

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 questions, spot spam, or draft replies for a human to approve") and redirects one class of work to list_reviews. It does not state explicit when-not conditions or name an alternative for per-channel comment listing, but the platform capability matrix effectively tells the agent where this tool does and does not apply.

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