Skip to main content
Glama
Sign In
Hermoso

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Fix a video beat

fix_beat

Re-renders only a specified 1.5-8s window of a video and splices it back on the video track, preserving all audio and remaining frames. Fixes a glitched shot without a full re-render, saving cost.

Instructions

Surgically re-render ONE time window (1.5-8s) of an existing rendered video and splice it back on the VIDEO TRACK ONLY — the rest of the video and ALL audio stay byte-identical. Use when one beat/shot is broken ('the shot at 8 seconds glitches') and a full re-render would waste the parts that worked; bills only the replacement clip's seconds (~1/3 of a full render). Do NOT pick a window covering spoken dialogue (a video-only splice under speech breaks lip-sync) — pass speechWindows to enforce this.

Input Schema

NameRequiredDescriptionDefault
dryRunNotrue = return the estimated credits this fix reserves and render nothing
promptYeswhat the replacement footage should show — describe the shot, matching the master's style
refImageNooptional product/style anchor image URL
videoUrlYesthe served URL of the master video to fix
endSecondsYeswindow end in seconds (window 1.5-8s)
startSecondsYeswindow start in seconds
speechWindowsNo[[start,end],...] windows with spoken lines — the fix window must not overlap these

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.435
    • changedInput schema / properties / dryRun / description
      Previous value: -"true = return the exact credits this fix reserves and render nothing"New value: +"true = return the estimated credits this fix reserves and render nothing"
  2. Changed1 schema field changedv0.1.320
    • addedInput schema / properties / dryRun
      Added value: +{
+  "description": "true = return the exact credits this fix reserves and render nothing",
+  "type": "boolean"
+}
  3. Changed1 schema field changedv0.1.161
    • changedOutput schema / (root)
      Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "jobId": {
-      "description": "the render job id — poll get_job with this id to resume or inspect",
-      "type": "string"
-    },
-    "model": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "description": "the product-facing label of the model that rendered it"
-    },
-    "raw": {
-      "description": "the raw job result payload (e.g. images[] for carousel template ads)"
-    },
-    "stillRendering": {
-      "description": "true when the render is still in progress — keep polling get_job with jobId",
-      "type": "boolean"
-    },
-    "url": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "description": "the served URL of the finished media (absent/null while still rendering)"
-    }
-  },
-  "type": "object"
-}New value: +null
  4. Addedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description adds rich behavioral context: only the VIDEO TRACK is replaced while 'the rest of the video and ALL audio stay byte-identical', billing is limited to the replacement clip's seconds (~1/3 of a full render), and a lip-sync failure mode is disclosed. This is exactly the kind of side-effect and constraint detail the annotations do not cover.

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 paragraph front-loads the core operation before moving to usage and the critical dialogue exclusion. Every sentence earns its place — no filler, no repetition.

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?

For a complex video-editing mutation with no output schema, the description covers purpose, constraints, side effects, and billing. It stops short of describing the return value or how an agent would know the job finished, leaving a small gap, but is otherwise sufficient for correct selection and invocation.

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 description coverage is 100%, so the baseline is 3. The description ties startSeconds/endSeconds to the 1.5-8s window and reinforces the purpose of speechWindows, but those details are already present in the schema; it adds little meaning beyond what the parameter descriptions provide.

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?

The description uses a precise verb+resource ('Surgically re-render ONE time window... of an existing rendered video and splice it back on the VIDEO TRACK ONLY') and immediately distinguishes this surgical fix from a full re-render. The quoted example ('the shot at 8 seconds glitches') reinforces the specific use case.

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?

It explicitly states when to use it ('Use when one beat/shot is broken... and a full re-render would waste the parts that worked') and when not to ('Do NOT pick a window covering spoken dialogue'). It also provides the corrective action ('pass speechWindows to enforce this'), leaving no ambiguity about the intended conditions.

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