Skip to main content
Glama

upload_article

Save an article from Markdown you provide (e.g. something you wrote, summarized or collected), with no URL to fetch. For a web page, use save_article instead. Each call creates a new article unless it repeats an earlier call's idempotencyKey. Returns the article's id and metadata with an excerpt, not the content (use get_entry for that).

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": {
      "content": "<content>",
      "title": "<title>"
    },
    "name": "upload_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYesArticle title as plain text (NOT Markdown or HTML). Do NOT HTML-escape it — write & not &amp;, since the title is rendered as literal text and an entity like &amp; would show up verbatim.
authorNoOptional author/byline override. Plain text (NOT Markdown or HTML). Do NOT HTML-escape it — write & not &amp;, since it is rendered as literal text.
contentYesArticle content in GitHub Flavored Markdown. Supports footnotes ([^1] … [^1]: …) and math ($…$ inline, $$…$$ display). Standard CommonMark: raw characters and HTML entities both work in the body (& and &amp; both render as &).
summaryNoOptional summary/excerpt override (e.g. an abstract you already have). Plain text (NOT Markdown or HTML). Do NOT HTML-escape it — write & not &amp;, since it is rendered as literal text. Clipped to ~300 characters.
collectionIdsNoOptional collection IDs to also add the article to (see create_collection)
idempotencyKeyNoOptional key (letters, digits, _ and -; up to 128) unique to this article. Pass the same key when retrying a call that timed out or failed: if the first attempt saved the article, it's returned instead of saving a duplicate.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover readOnly/destructive/openWorld, so the description's added value is the creation semantics: every call creates a new article unless an idempotencyKey repeats, and the response contains only metadata plus an excerpt. That return-shape disclosure is genuinely useful given there is no output schema. The only wrinkle is a mild tension with idempotentHint=false, though the description's key-based exception makes the annotation defensible rather than contradictory.

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 core action, then the sibling routing, then creation/idempotency semantics, then the return shape. No filler or repetition.

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?

With no output schema, the description correctly fills that gap by stating the call returns id and metadata with an excerpt rather than content. Combined with the sibling routing and idempotency note, nothing an agent needs to invoke this correctly is missing.

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 all six parameters are already documented in detail, including idempotencyKey retry semantics, collectionIds, and the no-HTML-escape rules. The description only restates the idempotency behavior and adds no new parameter meaning, so baseline 3 applies.

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 ('Save an article from Markdown you provide') and explicitly scopes it to content with 'no URL to fetch', which separates it cleanly from save_article. An agent can select between the two on the description alone.

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 an explicit exclusion plus the alternative ('For a web page, use save_article instead') and a follow-up routing hint ('use get_entry for that') for retrieving content. When-to-use and when-not-to-use are both stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.