Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Finish video

finish_video

Add reviewer-style proof pills and anti-AI film grain to an existing video URL, returning a new file without altering the original.

Instructions

Post-process an EXISTING rendered video (its served mp4 URL) with the proven direct-response 'reviewer' finish and/or a film-grain pass — no AI model, ~30s, a couple of credits. pills=true composites a header pill (e.g. '10/10 would buy again'), a brand-accent sub-pill, and 3-4 green-check proof pills cascading in on the beat (YOU author the copy: header ≤40 chars, sub ≤34, each point ≤44 — concrete real benefits, never fabricated stats). grain=true applies a subtle camera-grain finish that makes photoreal AI renders look phone-shot ('less AI') — works alone or with pills. Returns a NEW video; the original is untouched.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
subNoaccent sub-pill copy, ≤34 chars (usually the product/brand)
grainNodefault false — anti-AI film-grain finish
pillsNodefault true — set false for a grain-only pass
accentNobrand accent hex for the sub-pill
headerNoheader pill copy, ≤40 chars (required when pills is on)
pointsNo3-4 proof points, ≤44 chars each
videoUrlYesthe served URL of the video to finish (from a previous render/job)

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Despite having annotations, the description adds substantial behavioral detail beyond them: 'no AI model, ~30s, a couple of credits', the exact compositing behavior of pills, the anti-AI intent of grain, and crucially 'Returns a NEW video; the original is untouched' which reinforces destructiveHint=false. This is exactly the extra context annotations cannot carry.

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?

The core action is front-loaded in the first clause, and every sentence carries useful information about modes, cost, and return behavior. It is dense and slightly overloaded with em-dashes and parentheticals, and the char-limit repetition duplicates the schema, so it is not maximally tight.

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 no output schema, the description correctly carries the return contract ('Returns a NEW video; the original is untouched') plus cost, runtime, and the two operating modes. For a 7-parameter tool with one required field, an agent has everything needed to invoke it 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 baseline is 3, but the description meaningfully enriches semantics: it explains what pills=true composites (header pill, brand-accent sub-pill, cascading green-check proof pills), that grain applies a subtle camera-grain finish, and that the caller authors the copy with real (never fabricated) benefits. It repeats the char limits already in the schema, which limits it below 5.

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 states a precise verb and resource ('Post-process an EXISTING rendered video (its served mp4 URL)') and clearly distinguishes this finishing step from generation/editing siblings by naming the two passes it performs (reviewer pills, film-grain). An agent can tell it apart from generate_video, edit_video, or upscale_video without opening the 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?

It gives clear usage context: the input must be an already-rendered video URL from a previous render/job, and it explains the two modes ('pills=true ... grain=true ... works alone or with pills'). However, it never explicitly names an alternative tool or states when NOT to use it (e.g. versus edit_video or upscale_video), so routing is left partly to inference.

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