Skip to main content
Glama

Vixdeo — Tu Productor IA

by com.vixdeo
OverviewDiscussionsAdmin

Re-author with the LLM (paid)

author_op
Destructive

Runs ONE edit op that re-authors with the LLM — the SAME op the human director runs from the chat — and stages its result into the project's conversation draft, which becomes a new version when it is committed. The call waits up to 60 s for the pass (50 of the 58 authoring turns measured finished within that) and answers with the staged edit (outcome: completed_inline); a longer pass keeps running and the answer is its job (outcome: still_running, runId), which the project status reports by run_id. An identical call while the job runs, or within 15 minutes after it succeeded, returns the SAME job, so a retry is not charged twice; request_id names a deliberately repeated request. One authoring turn at a time per project (authoring-in-progress). Ops:

  • 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).

  • tighten_hook: Strengthen the opening hook (scene 0). LLM. Args: brief? (scene 0). Requires the write scope. Spends LLM budget (charged like a chat turn).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
opYes
argsYesOp arguments (see description).
project_idYes
request_idNoOptional: 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.

  1. Changed1 schema field changed
    • 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."
  2. Added

TDQS

A4.1/5.0
Behavior5/5

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

The description goes well beyond the annotations: it documents the 60 s wait window with measured hit rate, both outcome shapes (completed_inline vs still_running with runId), the 15-minute dedup window that makes retries free, request_id as an explicit repeat key, and the per-project concurrency limit. It also states the required write scope and that LLM budget is spent, which the destructive/idempotent hints do not convey.

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 behavior, timing, and dedup semantics are front-loaded and the op list is scannable. It is dense and occasionally repetitive (the retry/dedup idea is stated twice), but nearly every clause carries operational meaning.

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?

For a mutation tool with no output schema, the description supplies the return contract, timing behavior, idempotency story, concurrency constraint, and auth/budget requirements. An agent has everything needed to call it and interpret the response.

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?

With schema coverage at 50%, the description compensates by spelling out each op's args (scene_index, brief) and clarifying that brief re-authors the WHOLE scene, while request_id's 24 h key semantics are stated in both places. Only the nested args object remains loosely specified.

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 opening sentence gives a specific verb and resource: runs one authoring edit op that re-authors with the LLM and stages the result into the conversation draft. It enumerates the supported ops with their targets (rewrite_scene, tighten_hook), so purpose is unambiguous. It stops short of differentiating itself from near-siblings like run_op, stage_op, or rewrite_script, which are never named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied through the op list and the note that only one authoring turn runs at a time per project, plus the write-scope and budget caveats. There is no explicit when-to-use-this-vs-alternatives guidance despite several plausible siblings (run_op, stage_op, rewrite_script, direct).

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 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