Skip to main content
Glama
fruggr

Zendesk MCP Server by Fruggr

by fruggr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Create Article Attachment

create_article_attachment

Upload a file to a Zendesk Help Center article and receive the attachment's ID, name, type, size, and URL. Use for article assets; each call creates a new attachment.

Instructions

Upload a file to a Help Center article and return the created attachment (its id, file name, content type, size and content URL). Not idempotent: calling it again uploads another copy rather than replacing the previous one. This is for article assets — for files on support tickets use get_ticket_attachments, and to see an article's existing attachments use list_article_attachments.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file_nameYesName to store the file under, including its extension (e.g. "screenshot.png"); used as the download name.
article_idYesArticle ID — the numeric id of the Help Center article. Obtain it from list_articles or search_articles.
file_base64YesThe file's raw bytes as a base64-encoded string; the server decodes them before upload. At most 10420224 characters (about 7.45 MB of file); the HTTP transport additionally caps request bodies at 4 MB.
content_typeNoMIME type of the file, e.g. "image/png" or "application/pdf". Defaults to application/octet-stream when omitted.application/octet-stream

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.20.2
    • changedInput schema / properties / file_base64 / description
      Previous value: -"The file's raw bytes as a base64-encoded string; the server decodes them before upload."New value: +"The file's raw bytes as a base64-encoded string; the server decodes them before upload. At most 10420224 characters (about 7.45 MB of file); the HTTP transport additionally caps request bodies at 4 MB."
    • addedInput schema / properties / file_base64 / maxLength
      Added value: +10420224
  2. Addedv2.15.0
  3. Removedv2.14.0
  4. Changed3 schema fields changedv2.6.1
    • changedInput schema / properties / content_type / description
      Previous value: -"MIME type (e.g., \"image/png\", \"application/pdf\")"New value: +"MIME type of the file, e.g. \"image/png\" or \"application/pdf\". Defaults to application/octet-stream when omitted."
    • changedInput schema / properties / file_base64 / description
      Previous value: -"File content encoded as base64"New value: +"The file's raw bytes as a base64-encoded string; the server decodes them before upload."
    • changedInput schema / properties / file_name / description
      Previous value: -"File name (e.g., \"screenshot.png\")"New value: +"Name to store the file under, including its extension (e.g. \"screenshot.png\"); used as the download name."
  5. Changed1 schema field changedv2.6.0
    • changedInput schema / properties / article_id / description
      Previous value: -"Article ID"New value: +"Article ID — the numeric id of the Help Center article. Obtain it from list_articles or search_articles."
  6. Changed1 schema field changedv2.3.1
    • addedInput schema / additionalProperties
      Added value: +false
  7. First observedv1.7.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already mark the operation as non-idempotent, but the description adds concrete behavioral detail: calling it again uploads another copy rather than replacing the previous one. It also enumerates the returned fields despite the lack of an output schema, which is useful for an agent expecting a response.

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?

The description is compact and front-loaded: purpose and return value come first, followed by the non-idempotence warning and routing to alternatives. Every sentence earns its place, and there is no repetition of schema details.

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?

The description is complete for this tool's complexity. Parameters are fully documented in the schema, the return value is summarized, the non-idempotent behavior is explicit, and sibling tools are named for alternative use cases. Nothing critical is missing for an agent to invoke it correctly.

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 the schema fully documents all four parameters. The description does not add parameter-level semantics beyond the schema, but the baseline of 3 is appropriate since the schema carries the full burden and the description does not mislead.

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 description opens with a specific verb and resource: 'Upload a file to a Help Center article' and states what is returned. It also distinguishes itself from related tools by explicitly noting this is for article assets, not ticket attachments or existing attachment listing.

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?

The description gives clear selection guidance: use this for article assets; use get_ticket_attachments for support ticket files, and list_article_attachments to see existing article attachments. It also warns about non-idempotent behavior so an agent knows repeated calls create duplicates.

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