GenFlick

Save a GenAds experiment

native.genads_save_experiment

DestructiveIdempotent

Save a GenAds experiment. Use the exact saved revision; zero creates a new resource. Reuse operation_id after an uncertain response.

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.genads_save_experiment"
  }
}

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

A3.6/5.0

Behavior4/5

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

The annotations already declare destructive, idempotent and open-world behavior, so the description only needs to add context. It does add real value: the zero-revision rule discloses an upsert-style create path, and the operation_id reuse rule tells the agent how to safely retry after a timeout. It stops short of saying what a conflicting revision returns or what the save overwrites.

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?

Three short sentences, purpose first, then revision semantics, then retry semantics – nothing extraneous. The phrasing is clipped enough ("the exact saved revision") that a reader may need to re-read it against the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema is supplied and the annotations carry the safety profile, so the description only needs the tricky operational semantics. For a destructive, nested-body mutation it leaves out revision-conflict behavior and the request_key/operation_id relationship, which are the most likely sources of a wrong call.

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 50% and the description explains the meaning of two fields that the schema only types (expected_revision's zero case, operation_id's retry semantics). It says nothing about the difference between request_key and operation_id, or about read_skills proofs, which are the least self-explanatory required inputs.

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 names a specific verb and resource ("Save a GenAds experiment"), which is enough to separate it from read-side siblings such as native.genads_read_experiment_evidence or native.genads_link_experiment. It does not distinguish it from the other save_* siblings (save_genads_brief, save_genads_pack), so an agent must infer that this one writes the experiment record itself.

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?

"Use the exact saved revision; zero creates a new resource" gives concrete when-to guidance for the expected_revision value, and the operation_id retry rule covers the uncertain-response case. There is no explicit statement of when to pick this tool over native.genads_create_edit or native.create_genads_project, and no prerequisites are given.

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?