Skip to main content
Glama

Comment on a LinkedIn post

comment_create

Publishes a LinkedIn comment on a post or a reply under a comment as the signed-in member after approval checks, with a clipboard fallback if the API blocks sending.

Instructions

Comments on one post, or replies under one comment, as the signed-in member, through LinkedIn's /v2/socialActions endpoint. The pre-publish gates run first and can block it; the trusted helper then shows the comment in a dialog and sends it only on a yes. If LinkedIn refuses the endpoint (403), it and every later call put the text on the clipboard and open the post, for the member to paste and send. Stops while the halt file exists. With LINKEN_DRY_RUN=1 it sends nothing and returns the requests.

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": {
      "post": "<post>",
      "text": "<text>"
    },
    "name": "comment_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
postYesThe post: its URN (urn:li:activity:..., urn:li:share:... or urn:li:ugcPost:...) or its URL. A comment or reply link from "Copy link to comment" also works: it replies under that comment, with no parent needed.
textYesThe comment, as plain text, up to 1,250 characters.
parentNoTo reply under a comment: its URN, urn:li:comment:(urn:li:activity:...,...).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.1

TDQS

A4.1/5.0
Behavior5/5

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

Far exceeds what the annotations disclose: the pre-publish gates that can block the call, a confirmation dialog requiring a yes, the 403 fallback that copies text to the clipboard and opens the post, the halt-file stop condition, and the LINKEN_DRY_RUN=1 behavior that sends nothing and returns the requests. These are unobvious runtime traits an agent could not obtain from readOnlyHint/destructiveHint/openWorldHint.

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?

Five sentences, each carrying distinct operational information, front-loaded with identity and mode before the fallback behaviors. Some internal jargon ('the trusted helper', 'the pre-publish gates') is used without definition, costing a little clarity but no wasted sentences.

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 write tool with no output schema, the description covers success flow, blocking conditions, failure fallback, and dry-run behavior thoroughly. The one gap is that it never states what a successful call returns (other than in dry-run mode returning the requests), leaving the success response opaque.

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%, so the accepted URN/URL/comment-link formats and the 1,250-character limit are already documented per parameter. The description adds the conceptual model that 'post' plus 'parent' maps to comment-vs-reply, but supplies no format or edge-case detail beyond the schema, so the baseline of 3 applies.

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?

The description opens with a specific verb and resource: 'Comments on one post, or replies under one comment, as the signed-in member.' That scope is narrow enough to be clearly distinguished from post_publish (which creates posts) and reply_open, and it names the underlying endpoint so the agent knows the concrete target.

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 context is implied through the two modes (comment on a post vs. reply under a comment) and the note that 'Copy link to comment' workflows need no parent. However, it never explicitly states when to prefer this over a sibling such as post_publish or reply_open, so the agent must infer the boundary from verb choice alone.

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