Reach MCP — LinkedIn for AI agents

delete_comment

DestructiveIdempotent

Delete a LinkedIn comment: one the account wrote, or one written as a company page it administers. LinkedIn decides from the session's rights and refuses the others. Irreversible; confirm with the user and show the comment first. For a comment the account or one of its pages wrote; LinkedIn refuses comments of other people. No quota.

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": {
      "account_id": "<account_id>",
      "comment_urn": "<comment_urn>"
    },
    "name": "delete_comment"
  }
}

Input Schema

Name	Required	Description
`account_id`	Yes	Reach id of the LinkedIn account to act on, from list_accounts.
`comment_urn`	Yes	The comment: urn:li:comment:(…) from scrape_post, scrape_my_posts or list_page_activity, or urn:li:fsd_comment:(…).
`idempotency_key`	No	Optional. A key you choose (a UUID is fine) that names this exact call. If you retry with the same key and the same arguments, the first call's result is returned and nothing is done twice on LinkedIn. Reusing a key with different arguments is refused. Keys expire after 24 hours.

Output Schema

Name	Required	Description	Default
`deleted`	No
`comment_urn`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already flag destructiveHint and idempotentHint, but the description adds genuinely new context: the irreversibility warning, the authorization rule that LinkedIn decides from session rights, and the absence of a quota. The main gap is that it does not restate how the idempotency key protects retries, though the schema covers that.

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

Conciseness3/5

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

The action and its irreversibility are usefully front-loaded, but the ownership scope is stated twice in near-identical wording ('one the account wrote, or one written as a company page it administers' then 'For a comment the account or one of its pages wrote'), which wastes space in an otherwise short description.

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?

With an output schema present, return values need no explanation, and the description covers authorization scope, irreversibility, user confirmation, and quota status. It stops short of describing what a refusal or partial-permission outcome looks like, but that is a minor omission for a two-required-parameter mutation.

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 account_id, comment_urn, and idempotency_key are already fully documented with sources and semantics. The description adds no format, syntax, or selection guidance beyond the schema, which is the expected baseline when the schema does the work.

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 ('Delete a LinkedIn comment') and immediately bounds the scope to comments written by the account itself or by a company page it administers. The verb alone cleanly separates it from comment_post, reply_comment, and like_post among the siblings.

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

Usage Guidelines5/5

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

Gives explicit when-to-use and when-not-to-use conditions: only for comments the account or one of its pages authored, with LinkedIn refusing other people's comments. It also prescribes the operational precondition ('confirm with the user and show the comment first') rather than leaving confirmation to inference.

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

All Reach MCP — LinkedIn for AI agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?