Verified Handles

Draft an article

draft_article

Start a new article as a draft, as Console → Articles does: nothing is public until a publisher publishes it. The body comes in Markdown (the default) or HTML and is stored as cleaned HTML, through the site’s allowlist. The slug comes from the title when left out. Give what it is about and mentions (entries: their pages list it under “In the news”), the byline, a topic, and a hero image (an uploaded image’s media id) with its alt text. Audited with the key and the tool. Dry run by default: it shows the cleaned HTML exactly as it would be stored, the slug and the address it would have, the links the body makes (each entry’s title), and what the allowlist took out (dropped: each tag, and each attribute as tag@attribute, with how many), and checks what it can without writing.

Input Schema

Name	Required	Description	Default
`dek`	No	The standfirst under the headline, also the page’s description in search results; at most 300 characters.
`body`	No	The article’s text, in Markdown by default (body_format). A link to an entry is [Name](/<VHID>): it shows the entry’s current name while its text is that name. A heading “#” becomes a second-level heading (the title is the first). Raw HTML in Markdown is shown as text.
`kind`	No	"news" (the default) or "guide".	news
`slug`	No	The address’s last part: lower-case letters and digits in words split by single hyphens (e.g. "x-drops-legacy-checkmarks"), at most 80, never 11 digits.
`about`	No	The entries the article is about, in order (VHID, short name or QID).
`title`	Yes	The headline, at most 200 characters.
`topic`	No	A News article’s one topic: "verification" (Verification), "impersonation" (Impersonation and scams), "official-accounts" (Official accounts), "vh-data" (VH data), "vh-updates" (VH updates); or a guide’s group on the guides page: "check" (Check an account), "use" (Use Verified Handles), "contribute" (Get listed and help keep it right), "developers" (Developers and AI). null for none.
`authors`	No	The byline, in order: each author is an entry (VHID, short name or QID), at most 10. Whoever publishes may pick it again then.
`dry_run`	No	true (the default): write nothing — show the change and the exact request it would send. false: make the change.
`summary`	No	Why, in a few plain words, kept with the revision in the article’s history. Never an internal tracking ID.
`hero_alt`	No	The hero image’s alt text: what it shows, for a reader who cannot see it. Only with a hero image.
`mentions`	No	The entries it names in passing, in order.
`body_format`	No	"markdown" (the default) or "html": how `body` is written. Either is stored as cleaned HTML, through the site’s allowlist.	markdown
`hero_media_id`	No	The hero image: an uploaded image’s media id (upload_image, or media_catalog); null for none.

Output Schema

Name	Required	Description
`note`	No	A dry run: what to do next to make the change, in words.
`result`	No	A real run: the route’s own answer, where the tool adds facts of its own beside it.
`confirm`	No	A dry run of a change that needs it: the exact target to send back as `confirm` with dry_run: false.
`dry_run`	No	true: a dry run, which wrote nothing. Absent from a real run.
`replayed`	No	A real run with an idempotency_key already used for this change: the first call’s answer, given back; nothing was written now.
`would_send`	No	A dry run: the exact request the real run would send (`method`, `path`, any `headers` such as an Idempotency-Key, and its `body`, `form` or `query`), or the requests, in order.
`may_edit_live`	No	A dry run of a live edit: whether this key’s account may edit this entry live.
`refused_because`	No	A dry run the real run would be refused for: why, in words.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 28, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds substantial context beyond them: dry run is the default and never writes, content passes through an allowlist sanitizer, nothing is public until published, and calls are audited. This is exactly the extra behavioral detail annotations cannot convey.

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-loads the core action and the dry-run default, and every sentence carries information. It is dense and reads as one long block, which makes scanning the parameter guidance harder than a short bulleted structure would, but there is little wasted text.

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 an output schema present, the description does not need to explain return values, yet it still usefully describes what a dry run surfaces (cleaned HTML, slug, address, links, dropped tags/attributes). For a 14-parameter mutation tool with a default dry run, this is close to complete; only failure/validation behavior is left vague.

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 the baseline is 3, but the description adds real meaning: slug is derived from title when omitted, about vs mentions distinction (mentions appear under 'In the news'), hero_media_id refers to an uploaded image, and hero_alt accompanies it. It does not enumerate all 14 params, but the gaps are ones the schema already covers well.

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 — 'Start a new article as a draft' — plus how it relates to Console → Articles and the publish step. Combined with 'nothing is public until a publisher publishes it', an agent can distinguish this from update_article_draft or get_article without opening a schema.

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?

Implicitly scopes usage to creating new drafts and explains the dry-run-first workflow explicitly. It does not name update_article_draft as the alternative for editing an existing draft, so the create-vs-update boundary is left partly to inference.

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

All Verified Handles tools Inspect

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.