HelpCenter.io

Reply To HelpCenter Comment

helpcenter_reply_to_comment

Destructive

Post a comment on an article — as a reply to an existing comment, or as a new top-level one. Requires a write-scoped API key.

The reply is attributed to the user the API key was issued to; there is no author field to set, which is what makes it impossible to post under a reader's name. It publishes immediately and is visible on the article to readers, and the person being replied to is emailed.

NOT IDEMPOTENT: calling this twice posts two comments. There is no external_id equivalent here, so re-running a failed batch will duplicate. Read the thread back with helpcenter_get_article_comments before retrying.

The body is PLAIN TEXT. HTML is not interpreted — it renders as the characters it is made of — so send prose, not markup.

Args:

article_id (number, required): the article to comment on.
comment (string, required): the body, 1-5000 characters, plain text.
parent_id (number, optional): the comment being replied to. Must be a comment on THIS article. Omit for a new top-level comment.
lang (string, optional): defaults to the parent comment's language, or the site's default.

Returns: { status: "success", message, comment: {...} } with the created comment.

Errors: 403 if the key is read-scoped; 404 if the article is not in this help center, or parent_id is not a comment on it (including when parent_id names an internal team note); 422 if the body is missing or over 5000 characters.

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": {
      "article_id": "<article_id>",
      "comment": "<comment>"
    },
    "name": "helpcenter_reply_to_comment"
  }
}

Input Schema

Name	Required	Description
`lang`	No	Language code. Defaults to the parent comment's language, or the site's.
`comment`	Yes	The reply body, up to 5000 characters. PLAIN TEXT — HTML is not interpreted and renders as the characters it is made of, so do not send markup.
`site_id`	No	Which help center to act on: an id from helpcenter_list_sites. Needed when this connection reaches more than one help center; omit it when it reaches one. Applies to this call only — pass it on every call of a task, and ask the user which help center they mean if their request does not say.
`parent_id`	No	Id of the comment being replied to. Must be a comment on THIS article. Omit to post a new top-level comment.
`article_id`	Yes	Id of the article to comment on.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnly=false, destructive=true and idempotent=false, and the description goes well beyond them: attribution to the API key owner (no author field), immediate public visibility to readers, an email sent to the person replied to, and the concrete duplication consequence of re-running a failed batch. The plain-text rendering behavior of the body and the error taxonomy (403 read-scoped key, 404 for cross-article or internal-note parent_id, 422 for length) are exactly the behavioral detail an agent cannot infer from the schema.

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

Conciseness5/5

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

Front-loads the action and the two modes, then layers auth, side effects, idempotency, body format, args, return shape and errors in a scannable order. The all-caps markers on NOT IDEMPOTENT and PLAIN TEXT are load-bearing warnings, not decoration, and the args section is a compact restatement rather than padding.

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?

For a non-idempotent, publicly visible write tool with no output schema, the description covers everything an agent needs: auth scope, attribution, side effects (public visibility plus email), duplicate risk and recovery, input format constraints, the return shape, and each error code with its cause. Nothing material is left for the agent to guess.

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 the baseline is 3, but the description adds real meaning: parent_id must reference a comment on THIS article and a 404 results if it names an internal team note, and lang defaults to the parent comment's language rather than the site default. The plain-text/character-limit constraint on the body is reinforced in prose, which matters because it changes how the agent should format its input.

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 ('Post a comment on an article') and immediately disambiguates the two modes it supports — reply to an existing comment or a new top-level one. An agent can distinguish this from note-oriented siblings like helpcenter_reply_to_article_note because the resource is explicitly an article comment and the reply target is a comment id, not a note id.

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?

Gives clear conditional guidance for the key decision (supply parent_id to reply, omit it for top-level) and names the alternative tool for the recovery path ('Read the thread back with helpcenter_get_article_comments before retrying'). It also states the write-scoped key prerequisite. It stops short of explicitly excluding sibling tools such as helpcenter_reply_to_article_note, but the usage context is otherwise unambiguous.

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

All HelpCenter.io 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?