Skip to main content
Glama

Nova Cast

by io.github.r4v3n-art
OverviewDiscussionsAdmin

Publish Draft

publish_draft
Destructive

Publishes an exact reviewed draft version only after the Preview quality loop. Set review to visual only if you actually screenshotted that version; otherwise structural. Do not publish a failing layout. Success requires ok and receipt:paint. Failed rendering preserves the previous component.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
reviewYesvisual if you actually screenshotted this exact version after the Preview quality loop; structural if you only inspected source/metadata. Never claim visual without a screenshot. Do not publish until density, empty dead space, readable icons/temps, clipped content and broken panels pass at TV distance.
draftIDYes
versionYes
operationIDYes
controlTokenYes
overrideReasonNoOnly when deterministic lint reported error-level findings you have judged acceptable (for example decorative text intentionally cropped). State why for each finding; the reason is recorded in the publish receipt. Never use it to skip fixing readable content.
expectedRevisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / overrideReason
      Added value: +{
+  "description": "Only when deterministic lint reported error-level findings you have judged acceptable (for example decorative text intentionally cropped). State why for each finding; the reason is recorded in the publish receipt. Never use it to skip fixing readable content.",
+  "maxLength": 500,
+  "minLength": 12,
+  "type": "string"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / review / description
      Added value: +"visual if you actually screenshotted this exact version after the Preview quality loop; structural if you only inspected source/metadata. Never claim visual without a screenshot. Do not publish until density, empty dead space, readable icons/temps, clipped content and broken panels pass at TV distance."
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnly=false, openWorld=true, so the safety profile is known. The description adds genuinely new behavior: failure preserves the previous component (a key nuance against the destructive hint), and success is gated on 'ok and receipt:paint'. It omits auth/token requirements beyond the controlToken field name.

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?

Four dense sentences, all load-bearing, with the core action front-loaded and the success condition and failure semantics following. Slightly compressed but no 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?

For a destructive, no-output-schema publish operation, the description supplies the precondition, review-mode rule, success signal, and failure behavior. The remaining gap is undocumented identity/versioning parameters (controlToken, expectedRevision, version), which an agent needs to supply correctly.

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 only 29%, so the description must compensate, and it does so partly: it explains the review enum semantics and the purpose of overrideReason implicitly via 'do not publish a failing layout'. But operationID, controlToken, expectedRevision, draftID, and version carry no meaning in either place.

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 ('Publishes an exact reviewed draft version') with a qualifier that scopes it to a precise version. It is clearly distinguishable from siblings like prepare_draft, update_draft, and discard_draft without opening any 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?

Gives an explicit precondition ('only after the Preview quality loop'), a when-to-choose rule for the review parameter (visual only with an actual screenshot, otherwise structural), and a prohibition ('Do not publish a failing layout'). It does not name alternative tools, so it falls short of the 5 bar.

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

All Nova Cast toolsInspect
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.

Resources