Narracore Screenplay Formatter

Scene shootability diagnosis (AI cites, server scores)

diagnose_scenes

Scene-level "shootability" diagnosis for a screenplay, using the same ai-2.0 rules as narracore.cn: YOU (the calling AI) cite the evidence, the server validates it and computes the score — no LLM on the server. Two steps: (1) mode="material" (FREE) returns each scene as a numbered block list ([n] [type] text), the strict findings JSON schema, and 6 problem types (abstract_psychology, literary_summary, unfilmable_information, unclear_space, weak_visible_action, unplayable_direction); (2) after analyzing the material yourself, call mode="score" with findings=[{scene, summary, problems:[{type, severity(low|medium|high), evidence (verbatim quote from the material), blocks (ordinals), suggestion}]}]. The server maps ordinals to blocks, drops any finding whose evidence cannot be verified (that scene then scores null — never faked), and computes each scene's 0-100 score (severity-weighted evidence coverage, exact arithmetic) plus a reference-only structural baseline. One credit covers one screenplay for 24 hours across the screenplay tools. Failed calls are never charged. 剧本逐场影视化度诊断：AI 举证、程序算分（0-100，证据核验，无效即空不冒充）。

Input Schema

Name	Required	Description
`mode`	No	Required, one of material \| score: material (free) returns the numbered scene material + schema; score submits findings for validation and scoring.
`text`	No
`blocks`	No
`scenes`	No	material mode only: scene numbers (1-based) to render; default all
`findings`	No	score mode only: your per-scene findings
`request_id`	No	Idempotency key (optional)
`license_key`	No	License key NRC-XXXX-XXXX-XXXX-XXXX (optional — free daily quota works without one)
`input_format`	No	text (default): line-based screenplay text. blocks: typed blocks (e.g. from format_screenplay).

Output Schema

Name	Required	Description	Default
`ok`	Yes
`mode`	No
`tool`	No
`state`	No
`reason`	No
`scenes`	No
`schema`	No
`credits`	No
`message`	No
`overall`	No
`recovery`	No
`versions`	No
`conflicts`	No
`next_step`	No
`request_id`	No
`diagnostics`	No
`next_actions`	No
`problem_types`	No
`contract_version`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 11, 2026

changedInput schema / properties / mode / description

Previous value: -"material (free): numbered scene material + schema. score: submit findings, server validates and scores."New value: +"Required, one of material | score: material (free) returns the numbered scene material + schema; score submits findings for validation and scoring."

removedInput schema / properties / mode / enum

Removed value: -[
-  "material",
-  "score"
-]

removedInput schema / required
```
Removed value: -[
-  "mode"
-]
```

Changed1 schema field changedOct 5, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "conflicts": {},
+    "contract_version": {
+      "type": "string"
+    },
+    "credits": {
+      "additionalProperties": {},
+      "properties": {
+        "bundled": {
+          "type": "boolean"
+        },
+        "charged": {
+          "type": "number"
+        },
+        "free_tier_used": {
+          "type": "boolean"
+        },
+        "note": {
+          "type": "string"
+        },
+        "remaining": {
+          "type": [
+            "number",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "charged",
+        "remaining"
+      ],
+      "type": "object"
+    },
+    "diagnostics": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "block_id": {
+            "type": "string"
+          },
+          "code": {
+            "type": "string"
+          },
+          "line": {
+            "type": "number"
+          },
+          "message": {
+            "type": "string"
+          },
+          "severity": {
+            "type": "string"
+          },
+          "suggested_action": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "code",
+          "severity",
+          "message"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "message": {
+      "type": "string"
+    },
+    "mode": {
+      "type": "string"
+    },
+    "next_actions": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "billing": {
+            "enum": [
+              "free",
+              "bundled",
+              "charged"
+            ],
+            "type": "string"
+          },
+          "purpose": {
+            "type": "string"
+          },
+          "requires": {
+            "type": "string"
+          },
+          "reuse_fields": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "tool": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "tool",
+          "purpose",
+          "requires",
+          "billing",
+          "reuse_fields"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "next_step": {
+      "type": "string"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "overall": {},
+    "problem_types": {
+      "items": {},
+      "type": "array"
+    },
+    "reason": {
+      "type": "string"
+    },
+    "recovery": {
+      "additionalProperties": false,
+      "properties": {
+        "action": {
+          "type": "string"
+        },
+        "field_path": {
+          "type": "string"
+        },
+        "keep_request_id": {
+          "type": "boolean"
+        },
+        "note": {
+          "type": "string"
+        },
+        "resets_at_utc": {
+          "type": "string"
+        },
+        "retry_after_ms": {
+          "type": "number"
+        },
+        "retryable": {
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "action",
+        "retryable",
+        "keep_request_id"
+      ],
+      "type": "object"
+    },
+    "request_id": {
+      "type": "string"
+    },
+    "scenes": {
+      "items": {},
+      "type": "array"
+    },
+    "schema": {},
+    "state": {},
+    "tool": {
+      "const": "diagnose_scenes",
+      "type": "string"
+    },
+    "versions": {}
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

Changed4 schema fields changedOct 3, 2026
- addedInput schema / properties / findings / items / properties / problems / items / properties / severity / enum
```
Added value: +[
+  "low",
+  "medium",
+  "high"
+]
```
- removedInput schema / properties / findings / items / properties / problems / items / properties / severity / maxLength
```
Removed value: -16
```
- addedInput schema / properties / findings / items / properties / problems / items / properties / type / enum
```
Added value: +[
+  "abstract_psychology",
+  "literary_summary",
+  "unfilmable_information",
+  "unclear_space",
+  "weak_visible_action",
+  "unplayable_direction"
+]
```
- removedInput schema / properties / findings / items / properties / problems / items / properties / type / maxLength
```
Removed value: -64
```
Changed1 schema field changedSep 19, 2026
- addedInput schema / properties / blocks / items / properties / text / maxLength
```
Added value: +200000
```
AddedSep 16, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing the core behavioral contract: no server-side LLM, the server maps ordinals to blocks, drops findings whose verbatim evidence cannot be verified (scene then scores null, never faked), and computes a severity-weighted 0-100 score plus a reference-only baseline. It also covers billing behavior (1 credit/24h, failures not charged), which annotations cannot express.

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-loaded with the key contract (AI cites, server scores) and structured as a numbered two-step flow, so it reads efficiently despite its length. The trailing Chinese sentence restates the same content already given in English, which is mild redundancy.

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?

For a complex two-mode, credit-metered tool, it covers the workflow, the evidence-verification contract, failure handling, billing, and the free tier. An output schema exists, so return-value detail is correctly left to it, and nothing an agent needs to invoke either mode is missing.

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 75%, and the description adds real meaning: it explains the material/score mode split, the shape of findings=[{scene, summary, problems:[...]}], the six problem types, that evidence must be a verbatim quote, that blocks are ordinals, and that severity is low|medium|high. This meaningfully supplements the schema, though some field detail remains schema-only.

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 — scene-level 'shootability' diagnosis for a screenplay — and names the exact rule set (ai-2.0 / narracore.cn). It is clearly distinguishable from siblings like analyze_screenplay or format_screenplay because it defines a precise two-mode diagnostic job.

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?

The description gives explicit sequencing: call mode="material" first (free, returns material + schema), analyze yourself, then call mode="score" with findings. It also states credit scope (one screenplay for 24h across screenplay tools) and that failed calls are never charged. It does not, however, position itself against the other screenplay-analysis siblings, so 4 rather than 5.

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

All Narracore Screenplay Formatter tools Inspect

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.