GenFlick

request user input

native.request_user_input

DestructiveIdempotent

For creative discovery before kickoff, ask one useful question with waits_for_answer=no_default, an assumption that leaves the choice undecided, and final_reply. These three fields work together: leaving out waits_for_answer treats the question as optional and allows continued work. For accepted production work, ask only for material decisions or information/authority you cannot obtain, and use sensible reversible defaults for optional details. Recommend the best option and state its consequence. Ask the smallest set that unlocks useful work, then keep working: this returns at once with the question ids. Every question needs question and assumption. The assumption is the choice you go with until they answer, as the choice itself in a short phrase ("the experiment plan"): their card reads "Going with the experiment plan". Do the work that does not depend on the answer. Set waits_for_answer only when no reasonable choice exists and any guess would waste their work or credits (no_default), or the next step sends, publishes or deletes something that cannot be undone and no go-ahead covers it (irreversible, with that tool's id in held_tool). A waiting question still has an assumption: what you will do if they skip it ("leave the ending open"). Never wait for spending or video approval (the gates hold the paid step), a budget, or redundant permission to finish accepted work. During guided creative discovery, a choice the creator has not made is no_default: wait, with an assumption that leaves it undecided if skipped. Silence does not choose a proposed story or launch production. During already-authorized production, use sensible defaults within the accepted brief. Offer numbered options when the choices are few. Their answer or skip reaches you as an answer message at your next step. When this question is the response and no independent work remains, include final_reply and put any update_memory or settle_questions calls beside it; the question is saved and the turn waits without a second model call.

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.request_user_input"
  }
}

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

A3.9/5.0

Behavior4/5

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

The description discloses behavior beyond the annotations: the call returns immediately with question ids, the question is persisted, the turn then waits without a second model call, and the answer or skip arrives as an answer message at the next step. It also explains the creator-facing consequence of the assumption ('Going with the experiment plan') and that held_tool names the irreversible step being blocked. It does not address why annotations mark this destructiveHint=true, though nothing contradicts them.

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

Conciseness3/5

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

Every clause carries real policy, but the text is a single dense wall with stacked parentheticals and no upfront one-line statement of what the tool is. The most important instruction, that the call returns immediately and you keep working, is buried mid-paragraph, so an agent skimming may miss it.

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 six-parameter tool with nested question objects and an output schema, the description covers the decisions an agent must make: when to wait versus proceed, what the assumption means, how to size the question set, and how final_reply ends the turn. Remaining gaps (work_id, request_key, expected_catalog_version) are covered by schema descriptions, so the definition is nearly complete.

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 description coverage is 50% with nested objects, and the description compensates well for the arguments that matter: it defines waits_for_answer's two modes with the precise trigger for each, explains assumption with a concrete phrasing example and its waiting variant, ties held_tool to the irreversible mode, and explains when final_reply is required. The session plumbing parameters (work_id, request_key) are never mentioned, leaving the schema to carry them.

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 makes clear it asks the creator a question, records an assumption, and returns at once with question ids, which is specific enough for an agent to identify the resource and action. However, it never states the purpose in a single front-loaded sentence, and it never names the sibling it replaces (native.raise_work_question, native.answer_work_question, native.settle_questions), so differentiation is inferential rather than explicit.

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?

Strong conditional guidance: creative discovery before kickoff versus already-authorized production, when waits_for_answer should be left out, the two cases that justify waiting (no_default, irreversible), and explicit exclusions ('Never wait for spending or video approval... a budget, or redundant permission'). It loses a point because alternatives such as answer_work_question or settle_questions are mentioned only as adjacent calls, not as tools to choose instead of this one.

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?