Vixdeo — Tu Productor IA

Run an edit op (deprecated)

run_op

Destructive

DEPRECATED since 2026-09-27, kept until at least 2026-10-27: the edit ops are split by cost between two tools, one for the free deterministic ops and one for the paid LLM re-authoring ops (invocableVia in the op catalogue names them). This alias routes each op to the tool that owns it and answers what that tool answers, plus a deprecated notice that names it. Ops:

replan_scenes: Reorder the scenes (a permutation of indexes). Deterministic, $0. Args: order=[int...].
rewrite_scene: Re-author one scene (script and visual) under a brief. LLM. Args: scene_index, brief (the WHOLE scene is re-authored under the brief).
set_piece_fields: Set PIECE-level fields (production_score: silence_plan, music_intent, narrative_arc…), validated by the schema. Deterministic, $0. Args: fields (partial production_score: silence_plan, music_intent, narrative_arc, expected_total_duration_sec…; lists replace).
set_scene_fields: Set concrete fields of one scene (narration, duration, silences, infographic data…), validated by the schema. Deterministic, $0. Args: scene_index, fields (partial scene object: narrator_text, direction_notes, pre_silence_sec, pause_after_sec, visual.duration_target_sec, visual.prompt, infographic.data, kinetic_caption…; nested dicts merge by key, null deletes; validated by the VBP schema).
set_visual: Set a scene's visual type and/or visual prompt. Deterministic, $0. Args: scene_index, visual_type?, visual_prompt?.
swap_voice: Change the voice (semantic attributes) of one scene or all of them. Deterministic, $0. Args: voice_spec={...} (semantic attributes only: timbre, cadence, accent, language, apparent_gender, voice_style — NOT a voice id: the concrete voice is a piece-level decision made when the piece is created; a scene has no voice pin of its own, for the human either), scene_index?.
tighten_hook: Strengthen the opening hook (scene 0). LLM. Args: brief? (scene 0). Requires the write scope. The deterministic ops are $0. Spends LLM budget only on the authoring ops (charged like a chat turn); the deterministic ops are $0.

Input Schema

TableJSON Schema

Name	Required	Description
`op`	Yes
`args`	Yes	Op arguments (see description).
`project_id`	Yes
`request_id`	No	Optional: a caller-chosen key for this request (up to 64 characters). The same key returns the same job for 24 h; a new key runs it again. Without it, an identical call within 15 minutes is the same request.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 27, 2026

changedInput schema / properties / request_id / description

Previous value: -"Optional: a key of your own for this request (up to 64 characters). The same key returns the same job for 24 h; a new key runs it again. Without it, an identical call within 15 minutes is the same request."New value: +"Optional: a caller-chosen key for this request (up to 64 characters). The same key returns the same job for 24 h; a new key runs it again. Without it, an identical call within 15 minutes is the same request."

Changed1 schema field changedSep 27, 2026

addedInput schema / properties / request_id

Added value: +{
+  "description": "Optional: a key of your own for this request (up to 64 characters). The same key returns the same job for 24 h; a new key runs it again. Without it, an identical call within 15 minutes is the same request.",
+  "type": "string"
+}

First observedSep 27, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already flag destructive=true and idempotent=false, and the description adds substantial context beyond them: it requires the `write` scope, distinguishes $0 deterministic ops from LLM-charged authoring ops (billed like a chat turn), and notes that null deletes fields and that lists replace while nested dicts merge. It does not state reversibility of destructive ops, but the cost/scope/validation disclosure is well above baseline.

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 deprecation notice is front-loaded and the per-op bullet list is dense but earns its space, since each op has distinct args and cost behavior. The only real waste is the closing sentence, which repeats the '$0 for deterministic ops' fact a third time after it is already stated inside every bullet.

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 no-output-schema tool with nested args, the description is nearly sufficient: it explains routing, return behavior ('answers what that tool answers, plus a `deprecated` notice'), scope, cost, and per-op args. The remaining gap is that the successor tool names are not surfaced, forcing a `list_ops` lookup during a deprecation window.

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 50%, but the description compensates by documenting each enum value of `op` and the exact argument shape for every one (order=[int...], scene_index/brief, partial scene objects, voice_spec semantic-attribute caveat, etc.), far beyond the schema's 'see description' pointer for args. Only `project_id` is left implicitly understood, and it helpfully clarifies that swap_voice takes semantic attributes and NOT a voice id.

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 states exactly what the tool is: a deprecated alias that routes each edit op to the split tool that now owns it, and it enumerates all seven ops with their semantics. It distinguishes itself from siblings by declaring its deprecation and its routing role, but it never names the two replacement tools directly (it defers to `invocableVia` in the op catalogue), so the agent must take an extra step to find the successor.

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: DEPRECATED since 2026-09-27, kept until at least 2026-10-27, because ops were split by cost between two tools. The implied guidance is 'prefer the split tools', but the alternatives are only referenced indirectly through the op catalogue rather than named, so the when-to-use-this-vs-that decision is not fully closed.

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

All Vixdeo — Tu Productor IA tools Inspect

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

Need Help?