HelpCenter.io

Unschedule HelpCenter Change Set

helpcenter_unschedule_change_set

DestructiveIdempotent

Cancel a change set's scheduled publish. The set stays open with all its items; nothing is published and nothing is lost. Publish it later, or schedule it again, with helpcenter_publish_change_set.

A change set is a named release. It groups work that already exists — staged edits on published articles, never-published draft articles, and category visibility changes — and publishes all of it together, now or at a scheduled time. It owns no content: removing an item or deleting the set never deletes the work, which simply stays unreleased.

Use one when several articles have to go live at the same moment — a feature launch, a restructure, a coordinated translation. For one article, helpcenter_publish_staged_changes (or publishing a draft with helpcenter_update_article) is simpler. The flow: stage edits with helpcenter_stage_article_changes, or write drafts with helpcenter_create_article and published: false -> helpcenter_create_change_set -> helpcenter_add_change_set_items -> check readiness with helpcenter_get_change_set -> helpcenter_publish_change_set -> poll helpcenter_get_change_set_status until done.

Change sets are part of the Catalyst plan, behind the same gate as staged changes; on other plans the API answers 402.

Requires a write-scoped API key. Calling it on a set that is not scheduled is harmless.

Args:

change_set_id (number, required).

Returns: { status: "success", change_set: {...} } with is_scheduled false.

Errors: 403 if the key is read-scoped; 404 if the change set is not in this help center; 409 CHANGE_SET_NOT_OPEN if it has already started publishing or has published — too late to cancel.

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": {
      "change_set_id": "<change_set_id>"
    },
    "name": "helpcenter_unschedule_change_set"
  }
}

Input Schema

Name	Required	Description	Default
`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.
`change_set_id`	Yes	Id of the change set.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.3/5.0

Behavior4/5

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

The description goes well beyond the annotations, disclosing write-scope auth requirements (403 for read-scoped keys), the Catalyst plan gate returning 402, the 404 cross-help-center case, and the 409 CHANGE_SET_NOT_OPEN failure once publishing has begun. One tension: annotations set destructiveHint=true while the text insists 'nothing is published and nothing is lost' — an agent may read those as conflicting, though the text is arguably the more accurate account of a reversible, idempotent cancel.

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 purpose is correctly front-loaded in sentence one, but the body then spends two paragraphs explaining what a change set is, what it owns, and when to use one in general — conceptual background that is largely family-level rather than specific to unscheduling. The Returns/Errors/Args trailers are tight, but the middle is padded for a two-parameter cancel call.

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 mutation with no output schema, the description supplies the return shape ({ status: 'success', change_set with is_scheduled false }), the auth and plan prerequisites, and the three meaningful error cases. Combined with 100% schema coverage, an agent has everything needed to call it and interpret the result.

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 coverage is 100%, so both parameters are already documented; the description only restates change_set_id as required and adds nothing about its meaning. It never mentions site_id at all, even though the schema notes it must be passed on every call of a task and the user should be asked which help center they mean — a notable omission from the prose.

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 first sentence is a precise verb+resource statement: 'Cancel a change set's scheduled publish.' It immediately distinguishes this from helpcenter_publish_change_set and from the delete/update siblings by naming the exact state transition (scheduled to unscheduled). No ambiguity about what gets changed.

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?

Explicit routing is given: reschedule later with helpcenter_publish_change_set; for a single article use helpcenter_publish_staged_changes or helpcenter_update_article. It also states the full lifecycle context (stage -> create set -> add items -> get -> publish -> poll) so the agent knows where this call sits, and notes that calling it on a non-scheduled set is harmless.

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?