Skip to main content
Glama

Publish a LinkedIn post

post_publish

Publishes one LinkedIn post as the signed-in member after an approval dialog, returning its URN and URL and logging it locally; supports text with an optional image or PDF.

Instructions

Publishes one post to LinkedIn as the signed-in member: text alone, or text with one image or one PDF document. The pre-publish gates, when any are set, run first and can block the post. The trusted helper then shows the member the post in a dialog and sends it only on a yes. Returns the post URN and its URL, and appends one line to the local ledger. With LINKEN_DRY_RUN=1 it sends nothing and returns the requests it would send, in order. It does not schedule, edit or delete posts, mention people or companies, post to a company page, or upload video.

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": {
      "text": "<text>"
    },
    "name": "post_publish"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe post text, as plain text. Line breaks are kept. A word that starts with # becomes a hashtag. Every other character LinkedIn reserves is escaped, so it shows as typed.
mediaNoAbsolute path to one file to attach: .pdf, .png, .jpg, .jpeg or .gif.
titleNoThe document title LinkedIn shows on the post. Required when media is a PDF; not used for an image.
visibilityNoWho can see the post: PUBLIC (anyone) or CONNECTIONS (1st-degree connections only).PUBLIC

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.1

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 (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by disclosing that pre-publish gates run first and can block, that a confirmation dialog requires a 'yes', that a ledger line is appended, and that LINKEN_DRY_RUN=1 suppresses sending and returns the would-be requests. These are exactly the side-effect and control-flow facts an agent needs before invoking an open-world write.

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?

A single dense paragraph that front-loads what the tool does, then behavior, then return values, then exclusions. Every clause carries information, though the run-on packing of gates, dialog, return values, dry-run, and exclusions into one block slightly hurts scannability.

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?

No output schema exists, yet the description names what comes back (post URN and URL) plus the local ledger side effect and dry-run return shape. For a four-parameter open-world mutation, the confirmation gate, blocking behavior, and scope limits are all covered.

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 text, media, title, and visibility semantics are already fully documented in structured form. The description only reinforces the 'one image or one PDF' constraint and otherwise adds no new parameter detail such as path validation or visibility defaults.

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 ('Publishes one post to LinkedIn as the signed-in member') and immediately bounds the payload shapes to text-only, one image, or one PDF. This separates it cleanly from mutation siblings such as comment_create and from read-side tools like inbox_next.

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?

The closing sentence enumerates exclusions explicitly: no scheduling, editing, deleting, mentions, company-page posting, or video. That gives strong when-not-to-use signal, though it does not name a sibling to use instead for those excluded tasks.

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