User Intuition

Queue Interview Guide Design

queue_customize_study

Destructive

Queue one design turn that drafts or revises the study's discussion guide, questions, screener, and audience from the research brief. May fetch a researcher-provided concept URL. Clients that support MCP background tasks receive a task to wait on; other clients receive a job ID and poll get_customize_study_job. Then call get_study and show the full saved plan for human review. Reuse an idempotency_key after an uncertain response. Native concept images require the synchronous customize_study tool.

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": {
      "study_id": "<study_id>",
      "message": "<message>"
    },
    "name": "queue_customize_study"
  }
}

Input Schema

Name	Required	Description	Default
`message`	Yes	Research brief, requested revision, or answer to the previous design question.
`study_id`	Yes	UUID of the study, as returned by list_studies.
`decisions`	No	Use agent only when the human delegated research design choices.	human
`concept_image`	No	Native images are only supported by customize_study.
`idempotency_key`	No	Reuse the same key and inputs if a prior call timed out. A different operation needs a new key.
`organization_id`	No	Organization for this operation and billing. Use list_organizations to choose an active membership.
`execution_policy`	No	Control whether the study plan is a draft or should be reviewed before fieldwork.	review_before_fieldwork

Output Schema

Name	Required	Description	Default
`result`	Yes	Queued Customize Plan job.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 9, 2026

addedInput schema / properties / decisions / description

Added value: +"Use agent only when the human delegated research design choices."

addedInput schema / properties / execution_policy / description

Added value: +"Control whether the study plan is a draft or should be reviewed before fieldwork."

addedInput schema / properties / message / description

Added value: +"Research brief, requested revision, or answer to the previous design question."

addedInput schema / properties / study_id / description

Added value: +"UUID of the study, as returned by list_studies."

Changed1 schema field changedOct 22, 2026

changedInput schema / properties / organization_id / description

Previous value: -"Platform admins only: select an organization for this operation. Required when changing another organization’s study or using its wallet."New value: +"Organization for this operation and billing. Use list_organizations to choose an active membership."

AddedOct 2, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, openWorldHint=true, and readOnlyHint=false, and the description adds meaningful context: the external concept URL fetch, the async task-versus-job-ID split, and the idempotency_key retry pattern for uncertain responses. The gap is that destructiveHint=true is never explained – an agent is not told that a revision can overwrite or replace the existing design plan, which is the main risk of this call.

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?

Five short sentences, each carrying a distinct operational fact, with the core action front-loaded before the async and follow-up details. It is dense but every sentence earns its place.

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?

An output schema exists, so the definition does not need to explain return values, and it correctly covers async handling, retry semantics, and the required human-review step. The one missing piece relative to its complexity is the consequence of the destructive write on the existing study plan.

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 100%, so all seven parameters, including enums and defaults, are already documented in the schema. The description only restates the concept_image restriction and idempotency_key reuse rule, adding little beyond what the schema and annotations provide; baseline 3 applies.

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 ("Queue one design turn") and enumerates the resources it produces: discussion guide, questions, screener, and audience from the research brief. It also distinguishes itself from the closest sibling by noting that native concept images require the synchronous customize_study tool.

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 spells out the full operating sequence: wait on the MCP background task or poll get_customize_study_job, then call get_study and present the saved plan for human review. It also names a concrete alternative (customize_study) and the condition that selects it, so routing requires no inference.

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

All User Intuition 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.