StreamClipping AI

Start processing

start_clipping

Starts transcription and moment detection on a project in AWAITING_CROP status. Consumes processing minutes in proportion to the processed duration, plus one magic project if automatic mode is selected: from the monthly quota, then bought Magic, then one Credit from the wallet. When a Credit is spent, creditUsage gives the number of Credits used and left.

Input Schema

Name	Required	Description
`magic`	No	Automatic mode: framing, subtitles and editing chosen by the engine. Uses one magic project: from the monthly quota first, then from bought Magic, then one Credit from the wallet. When false, the project is left to be edited manually.
`projectId`	Yes	Project to process. It must be in AWAITING_CROP status.
`startAtSec`	No	Start offset in the source, in seconds. Useful to skip a waiting screen at the start of a stream.

Output Schema

Name	Required	Description
`hint`	Yes
`projectId`	Yes
`nextAction`	Yes
`creditUsage`	Yes	Set when this call paid with Credits from the wallet. null when no Credit was spent.
`waitSeconds`	Yes
`magicEnabled`	Yes
`shortenedToSec`	Yes	Set when the minutes balance did not cover the whole requested portion: only the first N seconds will be processed.
`magicSkippedReason`	Yes	Set if automatic mode could not be enabled although it was requested.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 24, 2026

changedInput schema / properties / magic / description

Previous value: -"Automatic mode: framing, subtitles and editing chosen by the engine. Consumes one magic credit. When false, the project is left to be edited manually."New value: +"Automatic mode: framing, subtitles and editing chosen by the engine. Uses one magic project: from the monthly quota first, then from bought Magic, then one Credit from the wallet. When false, the project is left to be edited manually."

addedOutput schema / properties / creditUsage

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "notice": {
+          "description": "The same information as one sentence, for example \"1 Credit used, 4 left.\"",
+          "type": "string"
+        },
+        "remaining": {
+          "description": "Credits left in the wallet after this call. null if the balance could not be read.",
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "spent": {
+          "description": "Credits taken from the wallet by this call.",
+          "type": "number"
+        }
+      },
+      "required": [
+        "spent",
+        "remaining",
+        "notice"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Set when this call paid with Credits from the wallet. null when no Credit was spent."
+}

changedOutput schema / required

Previous value: -[
-  "projectId",
-  "magicEnabled",
-  "shortenedToSec",
-  "magicSkippedReason",
-  "nextAction",
-  "hint",
-  "waitSeconds"
-]New value: +[
+  "projectId",
+  "magicEnabled",
+  "shortenedToSec",
+  "magicSkippedReason",
+  "creditUsage",
+  "nextAction",
+  "hint",
+  "waitSeconds"
+]

First observedOct 9, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Goes well beyond the annotations by disclosing the cost model: processing minutes proportional to duration and a magic project drawn in a stated order (monthly quota, then bought Magic, then wallet Credit), which also explains why the call is non-idempotent. It reports that creditUsage reveals Credits used and remaining, but says nothing about failure behavior or whether a partially processed project is resumable.

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 action and state requirement in the first sentence; the second sentence carries the cost chain. Dense and mostly waste-free, though the quota-ordering detail is verbose for the value it adds.

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 charged, non-idempotent mutation with an output schema and full annotation coverage, the description supplies the missing piece an agent needs — the economic consequence and where creditUsage comes from. Nothing essential to calling it correctly is absent.

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 including the magic mode and startAtSec offset are fully documented in the schema. The description adds only the cost consequence of magic=automatic mode, which is already largely restated by the schema field description, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a concrete verb pair (starts transcription and moment detection) and the resource (a project), plus the required AWAITING_CROP state. It doesn't explicitly contrast itself with nearby siblings like generate_clips or retry_project, but the action is specific enough to distinguish it from list/get tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The precondition 'project in AWAITING_CROP status' tells the agent when the call is valid, which is genuinely useful. However, it never says what to do when the project is in another status, or whether retry_project/cancel-type siblings are the fallback, so alternatives are left to inference.

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

All StreamClipping AI 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?