Skip to main content
Glama
Sign In
Zendesk MCP Server by Fruggr

Zendesk MCP Server by Fruggr

by fruggr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Update Help Center Article

update_article
DestructiveIdempotent

Modify article metadata—draft status, labels, section, visibility, author, or position—while preserving omitted fields; edit title or body via the translation tool.

Instructions

Update article metadata only (draft, promoted, labels as label_names, content tags as content_tag_ids, visibility as permission_group_id / user_segment_id, section_id, sort position, author, etc.) and return the updated article; fields you omit keep their value. Does NOT update content (title, body) — use update_article_translation for that, or update_article_section to edit one section. To put an article first or last in its section, prefer reorder_article: a plain position write is ambiguous while articles share position 0. To remove an article from the Help Center, use archive_article (a Guide admin can restore it); draft: true only unpublishes it.

Input Schema

NameRequiredDescriptionDefault
draftNoSet true to unpublish the article (revert to draft) or false to publish it.
positionNoSort position within the section (manual ordering only; 0 = first/top). New articles default to position 0. To move an article to the END of its section, set this to one more than the highest current position: read the highest position P from list_articles with sort_by="position", sort_order="desc", then set position = P + 1.
promotedNoSet true to promote (feature) the article in its section, or false to unpromote it.
author_idNoUser id of the article author (from search_users).
article_idYesArticle ID — the numeric id of the article to update. Obtain it from list_articles or search_articles.
section_idNoMove the article to this section (numeric id from list_sections).
label_namesNoLabel names for search ranking (use list_labels to see existing labels).
content_tag_idsNoContent tag ids to attach (use list_content_tags to find them).
user_segment_idNoUser segment that controls who can see the article (id from list_user_segments; if that is forbidden because the token is not a Guide admin, reuse the user_segment_id of an existing article from get_article).
permission_group_idNoGuide permission group controlling who can edit (id from list_permission_groups; if that is forbidden because the token is not a Guide admin, reuse the permission_group_id of an existing article from get_article).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.24.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Addedv2.15.0
  3. Removedv2.14.0
  4. Changed2 schema fields changedv2.12.1
    • changedInput schema / properties / permission_group_id / description
      Previous value: -"Guide permission group controlling who can edit (id from list_permission_groups)."New value: +"Guide permission group controlling who can edit (id from list_permission_groups; if that is forbidden because the token is not a Guide admin, reuse the permission_group_id of an existing article from get_article)."
    • changedInput schema / properties / user_segment_id / description
      Previous value: -"User segment that controls who can see the article (id from list_user_segments)."New value: +"User segment that controls who can see the article (id from list_user_segments; if that is forbidden because the token is not a Guide admin, reuse the user_segment_id of an existing article from get_article)."
  5. Changed9 schema fields changedv2.6.0
    • addedInput schema / properties / article_id / description
      Added value: +"Article ID — the numeric id of the article to update. Obtain it from list_articles or search_articles."
    • changedInput schema / properties / author_id / description
      Previous value: -"Author user ID"New value: +"User id of the article author (from search_users)."
    • changedInput schema / properties / content_tag_ids / description
      Previous value: -"Content tag IDs"New value: +"Content tag ids to attach (use list_content_tags to find them)."
    • addedInput schema / properties / draft / description
      Added value: +"Set true to unpublish the article (revert to draft) or false to publish it."
    • changedInput schema / properties / label_names / description
      Previous value: -"Label names for search ranking"New value: +"Label names for search ranking (use list_labels to see existing labels)."
    • changedInput schema / properties / permission_group_id / description
      Previous value: -"Permission group ID"New value: +"Guide permission group controlling who can edit (id from list_permission_groups)."
    • addedInput schema / properties / promoted / description
      Added value: +"Set true to promote (feature) the article in its section, or false to unpromote it."
    • addedInput schema / properties / section_id / description
      Added value: +"Move the article to this section (numeric id from list_sections)."
    • changedInput schema / properties / user_segment_id / description
      Previous value: -"User segment ID for visibility"New value: +"User segment that controls who can see the article (id from list_user_segments)."
  6. Changed1 schema field changedv2.3.1
    • addedInput schema / additionalProperties
      Added value: +false
  7. Changed1 schema field changed
    • addedInput schema / properties / position
      Added value: +{
+  "description": "Sort position within the section (manual ordering only; 0 = first/top). New articles default to position 0. To move an article to the END of its section, set this to one more than the highest current position: read the highest position P from list_articles with sort_by=\"position\", sort_order=\"desc\", then set position = P + 1.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}
  8. First observedv1.7.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the bar is lower, and the description still adds real context: partial-update semantics ('fields you omit keep their value'), that removal is a separate restorable archive operation, and that draft:true only unpublishes rather than deletes. It stops short of discussing auth/permission requirements for mutating an article, which is the main remaining gap for a destructive 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?

Front-loaded with the core action and scope, then layered exclusions and edge cases, with no filler sentences. It is dense and slightly overloaded as one long parenthetical paragraph, but each clause carries routing or behavioral information that would otherwise be lost.

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 10-parameter destructive mutation with no output schema, the description covers the return value ('return the updated article'), partial-update behavior, the metadata-vs-content boundary, and routing to every relevant sibling. Nothing an agent needs to call this correctly is missing.

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 baseline is 3, but the description earns extra credit by mapping business concepts to parameter names (labels as label_names, content tags as content_tag_ids, visibility as permission_group_id/user_segment_id) and by flagging that a raw position write is ambiguous when articles share position 0. The schema itself already carries the detailed per-field guidance (including the P+1 trick for moving to the end).

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 plus an explicit scope boundary: 'Update article metadata only ... and return the updated article', enumerating which fields count as metadata and which do not (title, body). It names the sibling tools it is not (update_article_translation, update_article_section, reorder_article, archive_article), so an agent can distinguish it without opening any schema.

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 rules with named alternatives and the condition that selects each: content edits go to update_article_translation or update_article_section, ordering goes to reorder_article, removal goes to archive_article. It also clarifies the subtle draft-vs-archive distinction, which is exactly the kind of disambiguation an agent needs.

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

Deploy Server

Other Tools