Skip to main content
Glama
Sign In

Super Artifacts

by app.superartifacts
OverviewDiscussionsAdmin

Read and answer the comments on an artifact

super_comments

Threads: messages, anchor, viewed version (default status: "open"); status all includes resolved history. Publish the fix first, then respond with body explaining what changed and which version, plus resolve: true atomically. Reuse messageId on retry. Reports replied/resolved separately. resolve: false reopens. screenshot returns an image. Agents cannot open/delete threads. mentioned: true lists your @mentions, oldest unseen first, marking them seen.

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": "super_comments"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoA path inside the artifact, e.g. "/pricing". Not pagination.
limitNo
reactNo
cursorNoThe previous cursor.next.
statusNo
resolveNo
respondNo
artifactNoArtifact id or slug.
mentionedNoWhere people @mentioned you instead of threads; artifact optional.
screenshotNoA message id, not a thread id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / react
      Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "emoji": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "on": {
+        "type": "boolean"
+      },
+      "thread": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "thread",
+      "message",
+      "emoji"
+    ],
+    "type": "object"
+  },
+  "maxItems": 20,
+  "type": "array"
+}
    • addedInput schema / properties / resolve
      Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 20,
+  "type": "array"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / respond / items / properties / body / description
      Previous value: -"A plain-text reply."New value: +"Explain the outcome and published version."
    • addedInput schema / properties / respond / items / properties / messageId
      Added value: +{
+  "description": "UUID reused on retry.",
+  "type": "string"
+}
  3. Changed2 schema fields changed
    • addedInput schema / properties / mentioned
      Added value: +{
+  "description": "Where people @mentioned you instead of threads; artifact optional.",
+  "type": "boolean"
+}
    • changedInput schema / required
      Previous value: -[
-  "artifact"
-]New value: +[]
  4. First observed

TDQS

B3.4/5.0
Behavior4/5

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

Annotations only declare openWorldHint=false and destructiveHint=false, so the description usefully adds that agents cannot open or delete threads, that status "all" surfaces resolved history while the default is open, that screenshot returns an image, that messageId is reused on retry for idempotency, and that mentioned: true silently marks mentions as seen. These are real behavioral facts beyond the annotations. It loses a point because several statements ("viewed version," "Reports replied/resolved separately") are too terse to act on confidently.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is compact and every clause carries information, but the structure is poor: semicolon-chained fragments with no front-loaded statement of what the tool does. The first clause is the least informative one, forcing the agent to reconstruct purpose from scattered hints.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, multi-mode tool with no output schema and only 50% schema coverage, the description covers the write-side behaviors well but leaves the read-side mechanics (pagination, page filtering, react semantics) and the response shape under-explained. An agent can act on the happy path but may need to guess on listing and reaction behavior.

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 coverage is 50%, and the description compensates for some parameters: it defines the default status of "open" and the meaning of "all", explains resolve: false reopens, describes what mentioned: true returns and its ordering, and clarifies screenshot returns an image. However, page, limit, cursor, artifact, and react receive no added meaning beyond the schema, and the messageId retry note merely restates the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a cryptic fragment, "Threads: messages, anchor, viewed version", which never plainly states the core action of reading comment threads and replying. The underlying purpose is only inferable from the title and the scattered references to respond/resolve/react/screenshot. It is distinguishable from all siblings (no other comment tool exists), but the verb+resource statement is left implicit.

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 concrete sequencing guidance: "Publish the fix first, then respond with body explaining what changed and which version, plus resolve: true atomically," and "resolve: false reopens." It also routes the agent between modes by explaining that mentioned: true serves @mentions while the default path serves threads. It stops short of naming explicit exclusions or alternatives for page/limit/cursor/react.

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