Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Analyze video

analyze_video

Break down a video's ad structure: get transcript, beat list, duration, and sampled frame times to study a reference before remixing.

Instructions

A video ad's structure: verbatim transcript (voiceover + on-screen text), beat list, duration and sampled frame times; study a reference before remixing it. ~A transcription call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesthe video URL (a served /generated/ path or a public http(s) video)
wordsNotrue | 'only': each spoken word's start/end
framesNoalso return the frames as images
anchorsNo{afterWord|beforeWord|atWord, occurrence?, offset?} -> s

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.285
    • addedInput schema / properties / anchors
      Added value: +{
+  "description": "{afterWord|beforeWord|atWord, occurrence?, offset?} -> s",
+  "items": {},
+  "type": "array"
+}
    • addedInput schema / properties / frames
      Added value: +{
+  "description": "also return the frames as images",
+  "type": "boolean"
+}
    • addedInput schema / properties / words
      Added value: +{
+  "description": "true | 'only': each spoken word's start/end"
+}
  2. Changed1 schema field changedv0.1.161
    • changedOutput schema / (root)
      Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "durationSeconds": {
-      "description": "the video length in seconds",
-      "type": "number"
-    },
-    "frameTimes": {
-      "description": "timestamps (seconds) of the sampled frames",
-      "items": {
-        "type": "number"
-      },
-      "type": "array"
-    },
-    "transcript": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "description": "verbatim voiceover + on-screen text with a beat list (null when silent/unreachable)"
-    }
-  },
-  "type": "object"
-}New value: +null
  3. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare openWorldHint=true, idempotentHint=false and destructiveHint=false, and the description's '~A transcription call.' hints that this is a compute/credit-bearing operation rather than a pure metadata read — relevant given readOnlyHint=false. But it does not explain the cost, latency, or async/non-idempotent behavior that the annotations imply.

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?

Very compact and front-loaded, leading with the returned structure and closing with the use case. It is telegraphic and sentence-fragmentary, which slightly hurts readability, but every clause earns its place.

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?

There is no output schema, and the description compensates by enumerating what is returned (transcript, beat list, duration, frame times). Combined with four annotated parameters and a required url, an agent has enough to invoke it correctly; only cost/async behavior remains undisclosed.

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 all four parameters (url, words, frames, anchors) are already documented in the schema. The description alludes to two of them ('transcript' for words, 'sampled frame times' for frames) but adds no syntax or format details beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

The description names a specific verb (analyze) and the exact artifact produced: verbatim transcript, beat list, duration and sampled frame times for a video ad. That is well beyond restating the title. Sibling differentiation is only implicit, via the phrase 'before remixing it', rather than naming a concrete alternative.

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?

'study a reference before remixing it' gives a clear triggering context for the tool and ties it to the remix/clone family (clone_video, remix_static, etc.). It stops short of stating when not to use it or naming a specific alternative tool, so it is context without exclusions.

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