Skip to main content
Glama
Sign In

Super Artifacts

by app.superartifacts
OverviewDiscussionsAdmin

Create or revise a template draft

super_template_save

Write a template draft only you can publish from. Without expectedVersion it creates (refused if the slug exists); with it, it revises the head (refused if the head moved past it), and a revision that changes nothing cuts no version. A json slot needs schema. Runtime files (≤512 KiB decoded) need a json slot and an index.html with one <script id="sa-template-values" type="application/json">. Others build from it only once super_release_template releases it; a revision never changes a released version.

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": {
      "slug": "<slug>",
      "title": "<title>",
      "description": "<description>",
      "spec": "<spec>"
    },
    "name": "super_template_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
demoNoSlug of your artifact to link as the demo (linked once public). "" clears it.
jobsNoWhat a person hires it for; the first is primary. Create default: from `kind`.
kindNo`dashboard`: a page that mostly shows live data — a label, not a capability.
slugYesKebab-case, 3–64 chars. Permanent.
specYes`slots`, `declaration` (every instance’s policy), optional `comments`, `keywords` (searched), `examplePrompts`.
filesNoRuntime files, `index.html` required. Omitting them on a revision drops the runtime from that new draft version only.
titleYes
promptNoA prompt a person copies to ask for one.
sampleNo`{"values": {…}}`, rendered in the preview.
audienceNo1–3, or `everyone` alone (the default).
categoryNoDeprecated; read as `jobs` when `jobs` is absent.
guidanceNoOptional notes for whoever fills it.
useCasesNoThings to build from it; the build prompt draws on them.
changeNoteNoRevisions: one line on why, for the changelog.
companionsNoExtra artifacts each publish makes at {slug}-{role}, same values (e.g. a stage for a host). Bind the primary with `source: {artifact: "@primary", streams}`. Released: add, never remove.
descriptionYes
installAfterNoYour note, appended to the build prompt as a suggestion.
samplePublicNoThe sample may appear on the public listing page.
expectedVersionNoThe version you revised. Present: revise. Absent: create.
installArchetypeNoAfter install: `scenarios` (default) offers three builds; `explainer` builds one from the sample; `interview` asks three questions first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / companions / items / properties / files / description
      Previous value: -"Runtime files, `index.html` required. Omitting it on a revision drops the runtime."New value: +"Runtime files, `index.html` required. Omitting them on a revision drops the runtime from that new draft version only."
    • changedInput schema / properties / files / description
      Previous value: -"Runtime files, `index.html` required. Omitting it on a revision drops the runtime."New value: +"Runtime files, `index.html` required. Omitting them on a revision drops the runtime from that new draft version only."
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare openWorldHint=false and destructiveHint=false; the description goes well beyond them with refusal conditions (slug collision, stale head), idempotence behavior (a no-change revision cuts no version), a 512 KiB decoded size cap, structural requirements for runtime files, and the invariant that a revision never alters a released version. That is precisely the mutation-side context an agent needs before calling.

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?

Purpose and the create/revise fork are front-loaded, and every sentence carries behavioral information rather than restating the name. The middle sentences are dense multi-clause run-ons (files constraints pack three rules into one sentence), which costs a little readability but not correctness.

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 20-parameter tool with nested objects and no output schema, the description covers the modes, the failure modes, the size ceiling, the file-structure contract, and the release boundary. It stops short of saying what a successful save returns (draft version identifier, validation errors), which is the one gap left by 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.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 90%, so the baseline is 3 and the schema already documents most fields. The description adds real meaning beyond it: the create/revise duality of `expectedVersion`, the rule that a `json` slot requires `schema`, and the `index.html` requirement with the exact `sa-template-values` script tag for runtime `files`. It does not touch the many remaining optional fields (companions, jobs, audience), but the schema carries those.

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 first sentence names a specific verb and resource — writing a template draft that only the caller can publish from — and the rest of the description immediately disambiguates the two modes (create without `expectedVersion`, revise with it). It also names the sibling `super_release_template` as the separate publishing step, so an agent can tell this apart from the release tool without opening either schema.

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?

The create-vs-revise rule is stated explicitly and operationally: absent `expectedVersion` creates (refused if the slug exists), present revises the head (refused if the head moved past it). It also states when others can build from the draft — only after `super_release_template` releases it — which is exactly the when-to-use routing an agent needs.

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

All Super Artifacts toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources