Clypmint

Fix captions

fix_captions

DestructiveIdempotent

Fix caption words or the key-word colour of a finished video, without a new edit; timing never moves. Either rewrite lines (from, to, text from get_project_context captions) or swap words everywhere with replace: [{ heard, spelled }] (brand names, people). To remember a spelling for future videos, use remember when available. Each spoken word keeps a caption word, so a 2-word name cannot become 1 word here: use remember plus revise_video. Free; 5 a day per video. Cost: Free: no credits.

Input Schema

Name	Required	Description
`color`	No	The key words' colour.
`lines`	No	The caption lines to rewrite, from get_project_context captions (from, to, text).
`replace`	No	Swap words everywhere they appear, e.g. a brand name: [{ heard: "Clip Mint", spelled: "ClipMint" }].
`video_id`	Yes	The video id from list_videos.
`base_version`	No
`operation_id`	No	A stable ID for this request. Preserve it on retries. Use a new ID only for a deliberate new request.

Output Schema

Name	Required	Description	Default
`code`	No
`cost`	No
`error`	No
`state`	No
`status`	No
`dry_run`	No
`message`	No
`plan_id`	No
`style_id`	No
`video_id`	No
`available`	No
`import_id`	No
`output_id`	No
`studio_url`	No
`version_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 13, 2026

changedInput schema / $schema

Previous value: -"https://json-schema.org/draft/2020-12/schema"New value: +"http://json-schema.org/draft-07/schema#"

Changed1 schema field changedOct 12, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Clypmint fix_captions result. Error results carry error; successful requests expose the identifiers and state available for the next step. Signed media stays in private metadata.",
+  "properties": {
+    "available": {
+      "type": "boolean"
+    },
+    "code": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "cost": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "dry_run": {
+      "type": "boolean"
+    },
+    "error": {
+      "type": "string"
+    },
+    "import_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "message": {
+      "type": "string"
+    },
+    "output_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "plan_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "state": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "status": {
+      "type": [
+        "string",
+        "integer",
+        "null"
+      ]
+    },
+    "studio_url": {
+      "format": "uri",
+      "type": "string"
+    },
+    "style_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "version_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "video_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}

AddedOct 12, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the destructiveHint/idempotentHint annotations, the description discloses a non-obvious invariant ("Each spoken word keeps a caption word"), a quota ("5 a day per video"), and cost ("Free: no credits"). The timing-never-moves guarantee also clarifies what destructiveHint actually touches here — the words/colour, not the timeline.

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 the core action and constraint, then routes to alternatives in a compact run of sentences. The trailing "Cost: Free: no credits." largely restates the earlier "Free; 5 a day per video" and could be dropped without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and annotations covering safety, the description supplies what structured fields can't: the fixed-timing invariant, quota, cost and the remember/revise_video fallback. The only unhinted parameter is base_version, whose role in conflict handling an agent must infer.

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?

Adds real meaning over an already 83%-covered schema: lines are sourced from get_project_context captions and carry from/to/text, and replace is explained as a global word swap with a concrete brand-name example ("Clip Mint" → "ClipMint"). color, base_version and operation_id get no prose, so it stops short of full coverage.

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 ("Fix caption words or the key-word colour of a finished video") plus a hard scope boundary — "without a new edit; timing never moves" — that separates it from revise_video and edit_video. An agent can pick this over siblings without opening any 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?

Gives explicit routing: rewrite lines pulled from get_project_context captions, or use replace for brand names/people. It also names the escape hatch for cases this tool can't handle ("a 2-word name cannot become 1 word here: use remember plus revise_video"), which is exactly the when-not guidance most definitions omit.

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

All Clypmint 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?