Skip to main content
Glama

PrePublish - YouTube script QA

by ai.prepublish
OverviewDiscussionsAdmin

Score the opening of a YouTube script

audit_hook

Score just the opening lines of a YouTube script: how much attention each sentence pulls, whether it opens a curiosity gap, how far away the payoff sits, plus the top issues and rewritten alternatives. Choose this when the user shares only a hook or opening paragraph, or wants a fast second opinion before auditing a whole draft. Cheaper and narrower than audit_script. This is a text-only check of an unrecorded script. It maps relative attention risk inside the draft. It does not measure or predict published YouTube retention, and it cannot account for delivery, editing, thumbnail, topic or distribution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
emailNoOnly needed once the free anonymous hook check for the day is used. Prepublish stores this address and may send a short series of follow-up emails about the check that include an unsubscribe link. Ask the user; never invent it. When the caller is authenticated with a Prepublish API key the result comes back in the conversation instead, so do not ask for an address in that case.
nicheNoChannel niche, only if the user said it. Sharpens the comparison.
hook_textYesThe opening lines exactly as written, ideally the first 15 to 30 seconds of speech.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
hookYesThe hook evaluation.
noticeYesThe scope limit that accompanies every Prepublish result. Repeat it to the user rather than dropping it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / email / description
      Previous value: -"Only needed once the free anonymous hook check for the day is used. Ask the user; never invent it. When the caller is authenticated with a Prepublish API key the result comes back in the conversation instead, so do not ask for an address in that case."New value: +"Only needed once the free anonymous hook check for the day is used. Prepublish stores this address and may send a short series of follow-up emails about the check that include an unsubscribe link. Ask the user; never invent it. When the caller is authenticated with a Prepublish API key the result comes back in the conversation instead, so do not ask for an address in that case."
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "hook": {
+      "description": "The hook evaluation.",
+      "properties": {
+        "created_at": {
+          "description": "When the evaluation was produced.",
+          "type": "string"
+        },
+        "evaluation_id": {
+          "description": "Prepublish id for this hook evaluation.",
+          "type": "string"
+        },
+        "grade": {
+          "description": "Letter grade for the opening.",
+          "type": "string"
+        },
+        "hook_text": {
+          "description": "The opening lines that were scored, echoed back.",
+          "type": "string"
+        },
+        "model_used": {
+          "description": "Which model produced this evaluation.",
+          "type": "string"
+        },
+        "niche": {
+          "description": "The niche the hook was compared against, when one was supplied.",
+          "type": "string"
+        },
+        "one_sentence_verdict": {
+          "description": "The single-sentence read on the hook.",
+          "type": "string"
+        },
+        "overall_score": {
+          "description": "Score for the opening as a whole.",
+          "type": "integer"
+        },
+        "rewrites": {
+          "description": "Alternative openings, each with its style and why that version works.",
+          "items": {
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "sentences": {
+          "description": "Per-sentence breakdown: the quote, its attention pull, its curiosity gap, how far off the payoff sits, and a note.",
+          "items": {
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "top_issues": {
+          "description": "The problems worth fixing first, each with a headline, the quote it applies to, and why it costs attention.",
+          "items": {
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
+    "notice": {
+      "description": "The scope limit that accompanies every Prepublish result. Repeat it to the user rather than dropping it.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "notice",
+    "hook"
+  ],
+  "type": "object"
+}
  3. Changed1 schema field changed
    • changedInput schema / properties / email / description
      Previous value: -"Only needed once the free anonymous hook check for the day is used. Ask the user; never invent it."New value: +"Only needed once the free anonymous hook check for the day is used. Ask the user; never invent it. When the caller is authenticated with a Prepublish API key the result comes back in the conversation instead, so do not ask for an address in that case."
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations are minimal (readOnlyHint false, openWorldHint true, destructiveHint false), so the description carries real load and does so: it discloses the email capture/retention side effect conceptually, frames the check as text-only on an unrecorded script, and bounds the scope by disclaiming retention prediction. What is missing is the concrete rate-limit/free-anonymous-quota behavior, which is only described in the schema parameter, not the tool description. No contradiction with annotations; the write-ish side effect is consistent with readOnlyHint=false.

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 when-to-use are front-loaded in the first two sentences, which is correct ordering. The second sentence is a long run-on of five comma-linked clauses, and the trailing limitation list is dense, but nearly every clause adds routing or scope information rather than 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?

With an output schema present, return values need not be explained, and the description covers the remaining agent needs: what the score covers, when to select it versus the sibling, the relative cost, and the explicit limits of the analysis. Nothing required to invoke it correctly is missing.

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 description coverage is 100%, so all three parameters (email, niche, hook_text) are already documented in the schema, including the email/auth nuance. The description adds no parameter-level detail beyond what the schema provides (e.g., hook_text length or format guidance is not repeated). Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Opens with a specific verb and resource ("Score just the opening lines of a YouTube script") and enumerates the actual outputs: attention pull per sentence, curiosity gap, payoff distance, issues, rewrites. It explicitly positions itself against the sibling audit_script as "cheaper and narrower," so an agent can distinguish the two 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?

States the selection condition directly: "Choose this when the user shares only a hook or opening paragraph, or wants a fast second opinion before auditing a whole draft." It also names the alternative (audit_script) and gives explicit when-not guidance by listing what the tool cannot assess (delivery, editing, thumbnail, topic, distribution).

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