Skip to main content
Glama

Create an Artifact

create_artifact

Publish an HTML page or a Markdown document as a Bisque Artifact: a persistent, versioned page at a stable URL that people can open, comment on, and that you can update later with update_artifact. Pass the whole document as content. The call waits for the page to be ready and returns its URL. It is private to you unless you pass audience or share_with. For a narrated presentation use create_presentation instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
iconNoAn emoji for the tab and listing, e.g. ๐Ÿ“Š.
typeNoDefault html.
titleYesA short name, the way a document or app is named.
listedNoShow it in listings (the org library, public discovery) rather than link-only. Default false.
contentYesThe full document. For html: a complete page (styles and scripts inline; it runs in a sandboxed frame with no network). For markdown: the Markdown source.
audienceNoWho can open the link. owner: only you. users: the people in share_with. public: anyone with the link.
share_withNoPeople to grant access by email (or uid), with a role. [{ "email": "ana@acme.com", "role": "viewer" }]. viewer opens it; editor can also publish new content. Implies audience "users" when audience is omitted.
descriptionNoOne sentence saying what the page is; shown in listings.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe viewer page.
iconNo
typeYes
titleYes
group_idNo
created_atNo
updated_atNo
version_idYesThe Version this call authored.
artifact_idYes
descriptionNo
audience_modeYesWho can open it: owner, users, org, or public.
version_numberNo
discoverabilityYes
organization_idNo
latest_version_idNo
publication_errorNo
publication_statusYesready means the URL serves this content now. queued or processing means it is still being prepared; call get_artifact to check. failed carries publication_error.
viewer_version_modeNo
published_version_idYesThe Version viewers see; null until a publication is ready.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, the description discloses meaningful behavior: the artifact is persistent and versioned, the call blocks until the page is ready and returns the URL, and visibility is private unless audience or share_with is provided. It also mentions the update capability and the stable URL. This adds real value beyond the structured annotations.

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 sentences, each earning its place: purpose, content requirement and behavior, privacy default, and sibling routing. The key facts are front-loaded and there is no redundant filler.

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?

Given the rich input schema, annotations, and output schema, the description covers all essential agent-facing concerns: what it creates, how to pass content, the blocking behavior, the return value, the default privacy, and how to select an alternative. Nothing critical is missing.

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. The description adds useful semantic reinforcement: 'Pass the whole document as content' clarifies the content parameter, and 'private to you unless you pass audience or share_with' clarifies the access-control behavior. This goes slightly beyond the schema descriptions.

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: publishing an HTML page or Markdown document as a persistent, versioned Bisque Artifact at a stable URL. It distinguishes the tool from create_presentation and update_artifact, making its purpose unmistakable.

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 gives clear context: publish a document, pass full content, wait for readiness, private by default unless audience/share_with is passed. It explicitly names create_presentation for narrated presentations and mentions update_artifact for later updates, though it does not enumerate when-not-to-use cases for every sibling.

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.

TDQS

A4.1/5.0
Disambiguation4/5

Tools are grouped into clear resource families (artifacts, artifact threads, presentations, channels) and descriptions explicitly redirect between create_artifact and create_presentation. The main potential confusion is create_presentation vs publish_narrated_presentation, since both produce presentations but differ in narration source; the descriptions do clarify this.

Naming Consistency5/5

All tools use snake_case verb_noun naming with consistent families like get_artifact, get_artifact_thread, and get_presentation_spec. publish_narrated_presentation is longer but still follows the verb_noun pattern, and there are no mixed casing styles or erratic naming conventions.

Tool Count4/5

19 tools is above the typical 3-15 range, but the count is justified by four clear subdomains: artifacts, artifact threads, presentations, and channels. No tools are redundant, though the set is large enough to feel slightly heavy.

Completeness4/5

Artifacts have full CRUD plus sharing, and threads have create/read/list/reply/resolve. Presentations cover authoring spec, creation/publishing, status, analytics, and reading context, but there is no delete or explicit update endpoint for presentations and no exposed way to fetch mentionables; these are workable gaps rather than fatal ones.

Resources