GenFlick

Prepare studio task

prepare_studio_task

Idempotent

Prepare one finite native studio task with exact saved source revision and finite total credit ceiling. This does not start work or confer approval. Briefs cannot broaden task, source access, budget, publication or recurring authority. Workshop develop_subject uses the exact typed subject: clip production/review, scene_reference 3D layout and camera paths, model geometry/motions, element media or writing. Native subject fences remain authoritative; scene_reference and model cannot invoke Film production.

Input Schema

Name	Required	Description
`task`	Yes
`brief`	No
`subject`	No	Canonical saved Workshop identity from Genflick. Clip and scene_reference address a Film clip through its native composite subject ID; writing addresses its saved document; model addresses an element. The retired scene kind is not accepted and must never be reinterpreted as a clip. IDs locate resources and never confer access.
`store_ids`	No	Exact customer-owned stores for this GenAds session or task. Requires separate commerce:read consent and current native store grants. No store writes, orders, customer data or advertising authority is granted.
`target_id`	No
`request_key`	Yes
`studio_kind`	Yes
`workspace_id`	Yes
`include_video`	No	Set true only when the task may generate video. A credit limit alone never authorizes video; the creator approves it separately in Genflick. Omitted means no video.
`ad_account_ids`	No	Exact advertisers for a GenAds session or task. Requires separate current ads scopes and native account grants. Creative credits do not authorize ad spend; each stage, activation or budget change still requires its saved human approval.
`maximum_credits`	Yes
`expected_revision`	Yes
`crm_connection_ids`	No	Exact customer-owned CRM connections for this GenAds session or task. Requires crm:read and current native access. Lead delivery additionally needs crm:deliver, source advertiser lead permission and exact native human approval; contacts never enter assistant results.
`genads_project_ids`	No	Exact additional GenAds homes for this Film or Series session or task. Each must already be selected in the current connection. Nesting alone grants no access.
`allow_genads_creation`	No	Permit creating native GenAds projects inside this Film or Series. Requires current projects:write and adds only each actually created child to this session and grant.
`analytics_connection_ids`	No	Exact customer-owned analytics connections selected for this GenAds session or task. Requires analytics:read and current native access. Reports preserve source attribution and data quality; this grants no analytics configuration, customer-level data, or advertising spend.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.6/5.0

Behavior4/5

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

The description adds critical behavioral context by stating that preparation is a non-operational step and cannot expand existing rights. This goes beyond the basic hints, clearly defining the scope of authority granted by the preparation action.

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?

While technical and dense, the description is highly efficient. Every sentence serves to define a functional boundary or a specific operational constraint, making the high information density acceptable for this complex tool.

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?

Given the multi-studio, conditional input schema, the definition provides a complete picture of the tool's operational envelope. The explicit limitations and specific usage cases for 'develop_subject' ensure the agent understands its scope completely.

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 only 50%, the description provides vital semantics for several concepts. It explains the specific operational nature of 'expected revision' and 'maximum_credits,' and details the acceptable subjects for the 'develop_subject' task type.

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 clearly states the tool's purpose is to 'Prepare one finite native studio task,' establishing a clear intent. It distinguishes itself by specifying constraints like 'exact saved source revision' and 'finite total credit ceiling,' which informs the agent exactly what kind of setup operation it performs.

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 provides explicit usage boundaries: the tool 'does not start work or confer approval,' and details that the 'brief cannot broaden task, source access, budget, publication or recurring authority.' This is definitive guidance on when and where *not* to use the tool.

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

All GenFlick 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?