Skip to main content
Glama

Valmera — agentic AI video editor

by io.valmera
OverviewDiscussionsAdmin

Build podcast shorts from explicit story arcs

make_shorts

PROJECT-SCOPED: this call acts only on the explicit project_id and returns the project identity with its result. Scout this LONG podcast/video for multiple complete story arcs and create LOCKED child projects. Valmera's internal agent may let the background scout choose the arcs. MCP callers MUST do the editorial selection themselves: read the full transcript, then pass clips with explicit source ranges and useful story context. The pipeline only seeds the selected source windows; it does not choose captions, framing, B-roll, music, effects or render a creative edit. Studio users explicitly press Edit on a card to boot a fresh editor. MCP callers open each child and perform the edits directly. It returns the scouting job ID; poll with wait_for_job or shorts_status. count only if the user named a number; else the scout keeps every story that clears the bar (no quota). An explicit clips array keeps every valid non-overlapping story arc, bounded only by source duration. Each clip must start and end on transcript sentence boundaries and last 10-120s; ranges must not overlap. snap='sentence' (the MCP default) moves a boundary to the nearest sentence edge within 1.5s and reports every move; snap='none' rejects instead. Every problem across all clips is reported in one reply. style_note is reference context for the eventual child editor, not a hard-coded recipe.

Input Schema

NameRequiredDescriptionDefault
snapNo
clipsYesCaller-authored story arcs. Required over MCP so the connected model chooses the shorts itself.
countNo
project_idYesRequired immutable scope for this call. Copy the id from list_projects/open_project/project_state; the active-project pointer is never used to guess.
style_noteNoOptional audience or reference context to preserve for the eventual editor.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / clips / items / properties / end / minimum
      Added value: +0
    • addedInput schema / properties / clips / items / properties / start / minimum
      Added value: +0
    • addedInput schema / properties / clips / items / properties / title / minLength
      Added value: +1
    • addedInput schema / properties / count / minimum
      Added value: +1
    • addedInput schema / properties / snap
      Added value: +{
+  "enum": [
+    "sentence",
+    "none"
+  ],
+  "type": "string"
+}
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only supply the safety profile (readOnly=false, idempotent=false, destructive=false), and the description adds substantial behavior beyond that: it is project-scoped and returns the project identity, it returns a scouting job ID requiring polling, the pipeline only seeds source windows and does not render a creative edit, snap moves are reported, and all clip problems are returned in one reply. This is rich, non-redundant disclosure.

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 content is dense and each sentence carries operational information, but the opening sentence front-loads scoping before stating the tool's core action, and the Studio-vs-MCP editor explanation is slightly verbose. It is longer than strictly necessary yet almost entirely non-redundant.

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 takes on the burden of explaining returns and does so (scouting job ID plus project identity, poll via wait_for_job/shorts_status). Combined with the mutation-safe annotations and full clip constraints, an agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60%, and the description compensates well beyond the schema: clips must start/end on transcript sentence boundaries and last 10-120s with no overlap; snap='sentence' (the MCP default) moves a boundary within 1.5s and reports every move while snap='none' rejects; count applies only if the user named a number; style_note is reference context for the eventual editor, not a recipe. This adds meaning the schema alone does not convey.

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 concrete verb and resource: scout a long podcast/video for complete story arcs and create LOCKED child projects (shorts). It clearly distinguishes this from siblings like apply_short_edit_batches, open_short, and critique_short by positioning itself as the arc-selection/child-creation step. An agent can tell what this tool produces 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 Guidelines5/5

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

It explicitly separates the MCP path (caller MUST do editorial selection by reading the transcript and passing clips) from the internal-agent path (background scout may choose arcs). It names follow-up alternatives (poll with wait_for_job or shorts_status, then open each child), and clarifies the count-vs-clips condition. When-to-use and when-not-to-use are both covered.

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

All Valmera — agentic AI video editor toolsInspect
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