GenFlick

Save an automation

native.save_automation

DestructiveIdempotent

Create an automation, or change one (give automation_id and its expected_revision). Save only when the creator asked for it to repeat. Always state the time zone and choose finite limits; say what you chose, including the monthly cap. An automation that spends advertising money, publishes, or was requested by an external assistant is saved as a draft until the owner approves that exact definition in Genflick; tell the creator where to approve it. Acceptance is not completion: read the runs.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "work_id": "<work_id>",
      "arguments": "<arguments>",
      "expected_catalog_version": "<expected_catalog_version>",
      "read_skills": "<read_skills>",
      "request_key": "<request_key>"
    },
    "name": "native.save_automation"
  }
}

Input Schema

Name	Required	Description
`work_id`	Yes
`arguments`	Yes
`read_skills`	Yes	Exact required native skills and their dependencies, copied from the accepted session bootstrap's skills array. Include only entries in that array. General mcp.* guides and native.{studio}.instructions are guidance, not native skill proofs.
`request_key`	Yes
`publication_proposal_id`	No	For native Social scheduling, the exact server-approved publication proposal. This identifier cannot confer approval by itself.
`expected_catalog_version`	Yes	For a new session, read a studios/{studio}/native/{pack} child toolset and copy invocation.catalog_version from a native tool descriptor. Do not use the top-level library version. For calls in an existing session, use that session proposal's catalog_version.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the destructive/openWorld/idempotent annotations, it discloses the draft-until-approved gate for money-spending, publishing, and externally-requested automations, names where approval happens, and warns that 'acceptance is not completion: read the runs.' That is exactly the kind of non-obvious workflow consequence an agent cannot get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Six short sentences, each carrying a distinct operational rule: creation vs update, the repeat requirement, timezone and caps, the approval gate, and the post-save verification step. No restatement of the title or filler, and the most decision-relevant content is front-loaded.

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 complex mutation tool with a rich output schema, the description covers the risky paths (draft approval, budget caps) that matter most. It leaves the session-scaffolding prerequisites (read_skills, expected_catalog_version, request_key) to schema descriptions, which is acceptable but not fully complete for a 5.

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 coverage is only 50% on a heavily nested six-parameter schema, so the description should carry more weight. It does add real intent to the allowance fields ('choose finite limits; say what you chose, including the monthly cap'), but the required work_id, request_key, read_skills, and expected_catalog_version are never addressed in the description text.

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 opens with a specific verb+resource pair and immediately splits the two modes ('Create an automation, or change one'), telling the agent exactly how to signal an update (automation_id plus expected_revision). It also implicitly separates itself from state/run siblings by scoping this tool to definition saving only.

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 a clear when-to-use rule ('Save only when the creator asked for it to repeat'), which is a genuine exclusion that prevents creating one-off automations, and it states the prerequisite for updates. It stops short of naming the sibling tools an agent would use instead (set_automation_state, run_automation_now, list_automations), leaving that routing to inference.

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?