Skip to main content
Glama
Upload-Post

Upload-Post

Official

Get post comments

get_post_comments
Read-only

List post comments on Instagram, Facebook, YouTube, LinkedIn, or TikTok using post ID or URL; pass a comment ID to fetch replies.

Instructions

List comments on a post. One endpoint for every network, chosen with platform. Identify the post by either postId or postUrl (YouTube: postId=videoId; LinkedIn: postId=the post urn; TikTok: postId=the video id, postUrl is not accepted). Add commentId to get the REPLIES hanging off that one comment instead of the post's top-level comments — replies are the same question with one more parameter, not another tool. TikTok: Requires the 'comments' capability on the profile's TikTok account (see the capabilities array in list_users). It is granted at connection time, so an account connected earlier has to reconnect TikTok before this works.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
userYesUpload-Post profile name.
afterNoPagination cursor returned by a previous call.
limitNoComments to return (1-50; that ceiling is both Meta's and TikTok's).
postIdNoPlatform media/post ID. YouTube: the videoId. LinkedIn: the post urn. TikTok: the video id (required — TikTok has no URL lookup).
postUrlNoPublic URL of the post.
platformNoSocial platform. One of instagram, facebook, youtube, linkedin, tiktok.instagram
commentIdNoReturn the replies under this comment instead of the post's top-level comments. Sent as `comment_id`.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.11.1
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • addedInput schema / properties / commentId
      Added value: +{
      +  "description": "Return the replies under this comment instead of the post's top-level comments. Sent as `comment_id`.",
      +  "type": "string"
      +}
    • changedInput schema / properties / limit / description
      Previous value: -"Comments to return (1-50, Meta's cap)."New value: +"Comments to return (1-50; that ceiling is both Meta's and TikTok's)."
    • changedInput schema / properties / platform / description
      Previous value: -"Social platform. One of instagram, facebook, youtube, linkedin. TikTok is unsupported."New value: +"Social platform. One of instagram, facebook, youtube, linkedin, tiktok."
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "instagram",
      -  "facebook",
      -  "youtube",
      -  "linkedin"
      -]New value: +[
      +  "instagram",
      +  "facebook",
      +  "youtube",
      +  "linkedin",
      +  "tiktok"
      +]
    • changedInput schema / properties / postId / description
      Previous value: -"Platform media/post ID. YouTube: the videoId. LinkedIn: the post urn."New value: +"Platform media/post ID. YouTube: the videoId. LinkedIn: the post urn. TikTok: the video id (required — TikTok has no URL lookup)."
    • removedOutput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  2. Changed3 schema fields changedv0.7.0
    • changedInput schema / properties / platform / description
      Previous value: -"Social platform. Only 'instagram' is currently supported."New value: +"Social platform. One of instagram, facebook, youtube, linkedin. TikTok is unsupported."
    • addedInput schema / properties / platform / enum
      Added value: +[
      +  "instagram",
      +  "facebook",
      +  "youtube",
      +  "linkedin"
      +]
    • changedInput schema / properties / postId / description
      Previous value: -"Platform media/post ID."New value: +"Platform media/post ID. YouTube: the videoId. LinkedIn: the post urn."
  3. First observedv0.4.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, but the description adds substantial behavioral detail: pagination via `after`, a hard limit of 50 (with reasoning), platform-specific ID formats, the switch to replies with `commentId`, and the TikTok prerequisite (capability granted at connection, requiring reconnection). These disclose behavior not evident from annotations alone.

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?

The description is moderately long but every sentence carries essential information: main purpose, platform handling, post identification, replies, and TikTok caveat. It is organized logically and avoids redundancy, though it could be slightly reorganized into clearer bullets for platform specifics. Overall, it is efficient without being verbose.

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?

Complete for a read-only, multi-platform comment-listing tool. The description covers platform quirks, capability prerequisites, pagination, replies, and limits. Combined with an output schema and annotations, an agent has everything needed to invoke it correctly across all supported networks.

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 every parameter is already documented. The description adds valuable enrichment: platform-specific meanings for `postId` (YouTube=videoId, LinkedIn=post URN, TikTok=video id with no URL lookup), the role of `commentId`, and the rationale for `limit`. This goes beyond the schema, though some details are already present in the property descriptions.

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 the specific action ('List comments on a post'), the resource (comments), and clarifies it is a single endpoint for all networks via `platform`. It clearly distinguishes listing from comment manipulation tools (reply, create, delete) and from analytics tools by focusing on the read-only retrieval of comments.

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?

Provides explicit guidance: to list comments use this tool; to get replies use the same tool with `commentId` (not another tool). It also covers platform-specific requirements (TikTok capability) and the fact that TikTok does not accept `postUrl`. Lacks an explicit 'when not to use this' compared to other read tools like `get_media` or `get_history`, but the comment-specific focus is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.