Skip to main content
Glama
miracleweasel

katto-mcp

by miracleweasel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

katto_rerender_clip

Re-render a finished clip with a new reframe layout or caption style. Keep the original, avoid video quota, and poll the returned rerender_id for the new clip URL.

Instructions

Re-render one already-finished clip with a new reframe layout and/or caption style (get valid caption_style values from katto_list_caption_styles). Free — does NOT use video quota. Each call starts a new render (not idempotent); the original clip is kept. Returns a rerender_id; poll katto_get_rerender for the new clip url.

Input Schema

NameRequiredDescriptionDefault
idYesJob id from katto_create_clip_job.
clip_indexYes0-based index of the clip to re-render.
layout_modeNoForce a reframing layout instead of letting detection choose one. Omit for automatic, which is what produces the best result on most clips.
caption_styleNoA caption style preset name. See katto_list_caption_styles for the labels.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.1
    • addedInput schema / properties / layout_mode / description
      Added value: +"Force a reframing layout instead of letting detection choose one. Omit for automatic, which is what produces the best result on most clips."
  2. Changed2 schema fields changedv0.5.6
    • changedInput schema / properties / caption_style / description
      Previous value: -"A caption style preset name."New value: +"A caption style preset name. See katto_list_caption_styles for the labels."
    • addedInput schema / properties / caption_style / enum
      Added value: +[
+  "default",
+  "hormozi",
+  "yellowPop",
+  "redAlert",
+  "skyline",
+  "bubblegum",
+  "aqua",
+  "violet",
+  "headline",
+  "centerPop",
+  "topLime",
+  "impactMax",
+  "bebasGold",
+  "robotoBold",
+  "montserratClean",
+  "poppinsSoft",
+  "robotoDoc",
+  "broadcast",
+  "wideClean",
+  "mono",
+  "bebasWhite",
+  "rainbow",
+  "multicolor"
+]
  3. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: it is free and consumes no video quota, every call starts a new render and is not idempotent (reinforcing idempotentHint=false), and the original clip is preserved (clarifying what destructiveHint=false means in practice). It also discloses the async contract — returns a rerender_id and requires polling via katto_get_rerender — which is not available from any structured field since there is no output schema.

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?

Three tight sentences, all front-loaded: what it does, its cost/idempotency profile, and the async follow-up. No sentence is filler and the most decision-relevant facts (free, not idempotent, original kept) come early.

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 4-parameter mutation with no output schema, the description covers the full agent loop: prerequisite lookup (caption styles), the async nature and polling target (katto_get_rerender), the cost model, and the non-destructive guarantee. An agent has everything needed to invoke and follow up correctly.

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 100% so the schema already documents each parameter, but the description adds meaningful framing: the 'and/or' wording signals that layout_mode and caption_style are independently optional while at least one change is expected, and it points to katto_list_caption_styles as the source of truth for caption presets. The enum values themselves are already in the schema, so the gain is modest.

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 ('Re-render one already-finished clip') plus the two dimensions that can change (reframe layout and/or caption style). It is clearly distinguishable from siblings like katto_adjust_clip, katto_retitle_clip, and katto_create_clip 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 Guidelines4/5

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

Gives clear context for use: an already-finished clip, at least one of layout/caption changing, and routes to katto_list_caption_styles for valid values and katto_get_rerender for polling. It does not explicitly contrast with alternatives such as katto_adjust_clip or when a full re-create is preferable, so it stops short of full when/when-not guidance.

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

Deploy Server

Other Tools