Skip to main content
Glama
Sign In

Help by DeltaBreen

by eu.deltabreen
OverviewDiscussionsAdmin

save_article

Write a help article, or change one. A new article is a draft and no customer sees it. Changing a published article changes only the words being written: the customer's site keeps what it has until publish_article. Give only what should change. Pro and higher.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "save_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoThe article, in a small Markdown: `## ` headings, paragraphs, `- ` and `1. ` lists, **bold**, `code`, fenced code, [links](https://…), and a picture on a line of its own as ![what it shows](https://…). A picture must be on one of the site's verified domains (list_domains). Up to 30,000 characters.
titleNoThe title, as a customer would ask it: "How do I get a refund?". Up to 120 characters. Needed for a new article.
sectionNoThe heading the help page lists it under, such as "Billing". Up to 40 characters; empty for none.
keywordsNoUp to 12 words or short phrases a customer types when they have this question. One of them typed in the form is enough for the article to be suggested, so choose their words, not yours. This replaces the list.
article_idNoThe article to change (a uuid), from list_articles. Leave out to start a new one.
product_idNoThe site a new article belongs to (a uuid), from list_products. Not needed when changing one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / article_id / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
    • changedInput schema / properties / body / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
    • changedInput schema / properties / keywords / type
      Previous value: -[
-  "array",
-  "null"
-]New value: +"array"
    • changedInput schema / properties / product_id / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
    • changedInput schema / properties / section / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
    • changedInput schema / properties / title / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds the substance: new articles are invisible drafts, edits to a live article are staged until publish_article, partial updates are the expected form, and the tool is gated to Pro plans and up. That's exactly the plan-gating and visibility context annotations can't express.

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?

Four short sentences, front-loaded with the create/update distinction, then the visibility consequence, then the edit contract, then the plan prerequisite. No sentence is filler.

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?

With no output schema, the description should ideally hint at what a save returns (e.g., the article id for later publishing), and it doesn't. Everything else an agent needs — draft semantics, publish dependency, partial-update rule, plan gating — is present.

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; the description earns above that by making the partial-update contract explicit ('Give only what should change'), which tells the agent not to send full objects that would overwrite the keywords list or section. It doesn't add format guidance beyond what the schema already gives per-field.

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+resource: 'Write a help article, or change one,' covering both create and update in one line. It also names the sibling whose effect it is not (publish_article), so an agent can place it in the workflow immediately.

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 a clear operating rule — 'Give only what should change' — and explains that new articles are drafts while edits to published ones don't go live until publish_article. It stops short of naming read-side siblings (get_article, list_articles) or unpublish_article, so the routing is clear but not exhaustive.

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

All Help by DeltaBreen toolsInspect
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