Skip to main content
Glama

PrePublish - YouTube script QA

by ai.prepublish
OverviewDiscussionsAdmin

Pre-flight a script against YouTube advertiser and monetisation policy

policy_preflight

Check a script before recording for the YouTube policy categories it may touch: which category families are implicated, the consequence family for each, a verdict and flag counts. Each category cites YouTube's own published policy page. Choose this when the user is writing about sensitive subject matter and asks whether it is safe to monetise. The quoted passages and their suggested rewrites are part of the paid audit, so the free result may return counts with locked quotes. It reports risk against published policy text; it is not a monetisation guarantee and does not speak for YouTube.

Input Schema

NameRequiredDescriptionDefault
titleNoThe planned title, if the user has one. Titles are checked too.
scriptYesThe script text as written, at least 200 characters. Below that there is not enough context for a policy read.

Output Schema

NameRequiredDescriptionDefault
noteYesSays which parts of the result are paid-only, so a locked field is not read as a clean pass.
noticeYesThe scope limit that accompanies every Prepublish result. Repeat it to the user rather than dropping it.
unlock_urlNoPresent only when part of this result is locked on the caller's plan: where the user pays to unlock it. Absent when nothing is locked.
unlock_offerNoPresent with unlock_url: the one sentence to relay when offering it.
policy_preflightYesThe policy read on this script.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedOutput schema / properties / unlock_offer
      Added value: +{
+  "description": "Present with unlock_url: the one sentence to relay when offering it.",
+  "type": "string"
+}
    • addedOutput schema / properties / unlock_url
      Added value: +{
+  "description": "Present only when part of this result is locked on the caller's plan: where the user pays to unlock it. Absent when nothing is locked.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "note": {
+      "description": "Says which parts of the result are paid-only, so a locked field is not read as a clean pass.",
+      "type": "string"
+    },
+    "notice": {
+      "description": "The scope limit that accompanies every Prepublish result. Repeat it to the user rather than dropping it.",
+      "type": "string"
+    },
+    "policy_preflight": {
+      "description": "The policy read on this script.",
+      "properties": {
+        "cached": {
+          "description": "True when this exact script and title had already been checked and the stored result was replayed.",
+          "type": "boolean"
+        },
+        "created_at": {
+          "description": "When the pre-flight was produced.",
+          "type": "string"
+        },
+        "preflight": {
+          "description": "The result itself: a verdict of \"no_matches\", \"review_suggested\" or \"high_matches\", the flags, counts_by_category, total_flags, whether the passages are locked, the rubric version it was scored against, the full category rubric with its citations, and the scope statement that must be shown with it.",
+          "type": "object"
+        },
+        "preflight_id": {
+          "description": "Prepublish id for this pre-flight.",
+          "type": "string"
+        },
+        "title": {
+          "description": "The title that was checked, when one was supplied.",
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "notice",
+    "policy_preflight",
+    "note"
+  ],
+  "type": "object"
+}
  3. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing a freemium split (quoted passages and rewrites are paid; the free result may return counts with locked quotes), a sourcing guarantee (each category cites YouTube's published policy page), and scope limits (not a monetisation guarantee, does not speak for YouTube). The annotations only say readOnlyHint=false, openWorldHint=false, destructiveHint=false, so this added context is genuinely valuable and consistent with them.

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 what it does and what it returns, then adds when-to-use, paywall behavior, and a disclaimer. Four sentences of mostly distinct content; the final disclaimer sentence is slightly defensive but earns its place by bounding the tool's authority.

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?

With an output schema present the description needn't enumerate return values, and it still sketches them. Combined with full schema coverage and the paywall/limits disclosure, an agent has everything needed to decide and call 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 100%, so both parameters (title, script) are already fully documented including the 200-character minimum rationale. The description adds nothing about parameter format or meaning, so the baseline of 3 applies.

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 — pre-flight a script against YouTube policy categories — and previews the exact output shape (category families, consequence family, verdict, flag counts). The monetisation framing distinguishes it from generic siblings like audit_script or check_authenticity without the agent needing to open 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?

Gives an explicit trigger: 'Choose this when the user is writing about sensitive subject matter and asks whether it is safe to monetise.' That is a clear use condition, but it names no alternative sibling or when-not-to-use case, so it stops short of full routing guidance.

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

All PrePublish - YouTube script QA 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