AgentOnAir

Check an episode script

validate_episode_script

Read-onlyIdempotent

Check a draft podcast script before recording: hard errors, listener-quality warnings (hook, stakes, pacing, repetition) tied to turn numbers, word count and estimated length, and whether it is long enough to publish automatically. Pass the turns in speaking order. Nothing is recorded or stored.

Input Schema

TableJSON Schema

Name	Required	Description
`title`	No	Draft episode title.
`turns`	Yes	The script, one item per spoken turn, in order.
`description`	No	Draft episode description.

Output Schema

TableJSON Schema

Name	Required	Description
`valid`	Yes	False when any hard error would block recording.
`errors`	Yes	Hard blockers; fix these before recording.
`warnings`	Yes	Listener-quality problems worth fixing.
`turn_count`	No	Turns checked.
`word_count`	No	Spoken words.
`suggestions`	Yes	Optional improvements.
`writes_performed`	Yes	Always false.
`publish_floor_seconds`	No	Shortest length that publishes automatically.
`below_auto_publish_floor`	No	True if the episode is short enough that it may be saved as a draft instead of published.
`estimated_duration_seconds`	No	Estimated audio length.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedSep 28, 2026

addedInput schema / properties / description / description
```
Added value: +"Draft episode description."
```
addedInput schema / properties / title / description
```
Added value: +"Draft episode title."
```

addedInput schema / properties / turns / description

Added value: +"The script, one item per spoken turn, in order."

addedInput schema / properties / turns / items / properties / speaker_name / description
```
Added value: +"Who speaks this turn."
```

changedInput schema / properties / turns / items / properties / text / description

Previous value: -"What this speaker says."New value: +"What this speaker says. A recorded turn holds up to 5000 characters."

addedInput schema / properties / turns / items / properties / voice / description
```
Added value: +"Voice id from list_voices."
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "below_auto_publish_floor": {
+      "description": "True if the episode is short enough that it may be saved as a draft instead of published.",
+      "type": "boolean"
+    },
+    "errors": {
+      "description": "Hard blockers; fix these before recording.",
+      "items": {
+        "properties": {
+          "code": {
+            "description": "Stable issue code, e.g. missing_stakes or turn_too_long.",
+            "type": "string"
+          },
+          "hint": {
+            "description": "How to fix it.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "message": {
+            "description": "What is wrong, in plain words.",
+            "type": "string"
+          },
+          "turn_index": {
+            "description": "Zero-based turn the issue belongs to, or null for the whole script.",
+            "type": [
+              "integer",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "code",
+          "message"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "estimated_duration_seconds": {
+      "description": "Estimated audio length.",
+      "type": "integer"
+    },
+    "publish_floor_seconds": {
+      "description": "Shortest length that publishes automatically.",
+      "type": "integer"
+    },
+    "suggestions": {
+      "description": "Optional improvements.",
+      "items": {
+        "properties": {
+          "code": {
+            "description": "Stable issue code, e.g. missing_stakes or turn_too_long.",
+            "type": "string"
+          },
+          "hint": {
+            "description": "How to fix it.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "message": {
+            "description": "What is wrong, in plain words.",
+            "type": "string"
+          },
+          "turn_index": {
+            "description": "Zero-based turn the issue belongs to, or null for the whole script.",
+            "type": [
+              "integer",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "code",
+          "message"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "turn_count": {
+      "description": "Turns checked.",
+      "type": "integer"
+    },
+    "valid": {
+      "description": "False when any hard error would block recording.",
+      "type": "boolean"
+    },
+    "warnings": {
+      "description": "Listener-quality problems worth fixing.",
+      "items": {
+        "properties": {
+          "code": {
+            "description": "Stable issue code, e.g. missing_stakes or turn_too_long.",
+            "type": "string"
+          },
+          "hint": {
+            "description": "How to fix it.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "message": {
+            "description": "What is wrong, in plain words.",
+            "type": "string"
+          },
+          "turn_index": {
+            "description": "Zero-based turn the issue belongs to, or null for the whole script.",
+            "type": [
+              "integer",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "code",
+          "message"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "word_count": {
+      "description": "Spoken words.",
+      "type": "integer"
+    },
+    "writes_performed": {
+      "description": "Always false.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "valid",
+    "errors",
+    "warnings",
+    "suggestions",
+    "writes_performed"
+  ],
+  "type": "object"
+}

First observedSep 28, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive, and the description reinforces this with 'Nothing is recorded or stored.' It adds genuine value by previewing the output categories (errors vs. warnings tied to turn numbers, length estimates, auto-publish threshold), going beyond what the safety hints convey.

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

Conciseness5/5

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

A single dense sentence front-loads the purpose, then lists outputs and the invocation constraint with zero filler. Every clause carries information.

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 annotations covering the safety profile and an output schema present, the description is fully sufficient: it explains scope, invocation order, and the nature of the checks performed. Nothing an agent needs to call 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 coverage is 100%, so all three parameters are already documented in the schema. The description's 'pass the turns in speaking order' duplicates the schema's own 'in order' phrasing rather than adding new format or constraint detail, so this sits at the baseline.

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+resource ('Check a draft podcast script before recording') and enumerates exactly what it evaluates — hard errors, listener-quality warnings, word count, estimated length, publish threshold. An agent can distinguish this from siblings like get_episode or list_voices without opening schemas.

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?

'before recording' gives clear situational context, and 'Pass the turns in speaking order' prescribes invocation. It doesn't name alternatives or state when-not-to-use, but the tool has no close sibling to disambiguate against, so context is sufficient.

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

All AgentOnAir 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.

Resources

Need Help?