Skip to main content
Glama

Update Article

hudu_update_article
Idempotent

Update an existing Hudu knowledge-base article by replacing one or more of its fields. Pass only the fields to change; each supplied value wholly replaces the stored one.

Instructions

Update an existing article. An article is a knowledge-base document: HTML content, optionally filed in a folder and optionally scoped to one company. Articles with no company are global to the instance.

Only the fields you supply are sent. Be aware that Hudu applies these as a PUT: for fields you do send, the new value replaces the old one outright — read the record first with hudu_get_article if you intend to append rather than overwrite.

Operation class: Update. Impact: Overwrites the supplied fields on this article.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesNumeric Hudu id of the article.
nameNoTitle of the article, shown in lists and search.
contentNoBody of the article, as HTML. Hudu stores this string and renders it as HTML in the knowledge base, so Markdown passed here is stored literally and shown to readers with its asterisks, hashes and pipes intact — convert to HTML (<h2>, <p>, <ul>, <table>, <a href="...">) before sending. Existing content is replaced wholesale on update, not appended to.
folder_idNoNumeric id of the folder to file the article under, from hudu_list_folders. Omit to leave the article at the top level. Pick a folder whose own company matches the article's — Hudu does not document what it does with a mismatch.
company_idNoNumeric id of the company whose knowledge base this article belongs to. Omit it to create a global article that is visible across every company. Resolve a customer name to an id with hudu_list_companies first.
enable_sharingNoPUBLISHES THIS ARTICLE TO THE PUBLIC INTERNET when set to true. Hudu mints a share URL (returned as `share_url` on the record) that renders the full article content to anyone holding the link, with no Hudu login, no company scoping and no record of who read it. Client documentation frequently contains internal hostnames, procedures and account references, so treat this as a disclosure decision rather than a formatting one: leave it unset unless the user has explicitly asked for a link they can send outside their Hudu tenant, and tell them what the article contains before you set it. Setting it to false withdraws an existing public URL.
Behavior5/5

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

The description discloses that only supplied fields are sent, that Hudu applies a PUT (replace, not merge), and that overwriting is outright. This goes beyond annotations (readOnlyHint false, destructiveHint false) by explaining partial update semantics and the need to read before appending.

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?

The description is well-structured: it starts with a clear definition, then explains update behavior, and ends with operation class. It is slightly verbose but every sentence contributes value.

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?

For a tool with six parameters and no output schema, the description covers the core concepts (article, company scoping, global articles, overwrite semantics). It also points to hudu_get_article for append scenarios. It does not describe return values or error handling, but these are not required given the absence of an output schema.

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 parameters are well-documented. The description adds only general method-level semantics (PUT, partial update) without adding new parameter-specific meaning beyond the schema. It does clarify that 'only the fields you supply are sent,' but that is implied by the schema.

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 clearly states the tool updates an existing article and defines what an article is (knowledge-base document with HTML content, optional folder and company scoping). It distinguishes from siblings like hudu_create_article (creation) and hudu_get_article (read-only).

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?

The description provides clear usage context: it's for updating existing articles, and explicitly advises reading first with hudu_get_article before appending. It does not explicitly mention when to use create versus archive, but the purpose is clear enough.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ZenixSolutions/hudu-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server