Uxia

Generate Interview Study

generate_interview_study

Create an AI-moderated interview study from a brief: research goals, discussion guide and intro, saved as a draft. Takes 1–3 minutes. Returns the guide and a url to edit it in Uxia; share it as a link. On insufficient_brief nothing is created: ask the user the listed questions, then retry. No recruiting or launch.

Input Schema

Name	Required	Description	Default
`depth`	No	Interview length: 2–5, 5–10 or 10–15 min.	balanced
`title`	Yes
`objective`	Yes	The user's brief in their own words: what to learn, from whom, why.
`companyContext`	No	Optional; URLs are researched.
`productContext`	No	Optional; URLs are researched.
`researcherBriefing`	No	Optional guidance for the AI moderator.

Output Schema

Name	Required	Description
`url`	No	The study in the Uxia builder. Share it as a clickable Markdown link so the user can review and edit it.
`goals`	No	The generated discussion guide: research goals and their questions.
`title`	No
`status`	Yes	insufficient_brief: nothing was created; ask the user the questions in reasons and call again.
`testId`	No	Internal identifier for follow-up tool calls such as get_interview_study.
`reasons`	No	Why the brief was too thin, with a suggestion for each.
`language`	No	Language the study was written in (BCP-47).
`estimatedMinutes`	No	Planned interview length.
`screeningQuestions`	No	Questions participants answer before the interview; an answer with qualifies false screens them out.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026

addedOutput schema / properties / screeningQuestions

Added value: +{
+  "description": "Questions participants answer before the interview; an answer with qualifies false screens them out.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "allowMultiple": {
+        "type": "boolean"
+      },
+      "options": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "label": {
+              "type": "string"
+            },
+            "qualifies": {
+              "type": "boolean"
+            }
+          },
+          "required": [
+            "label",
+            "qualifies"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "question": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "question",
+      "allowMultiple",
+      "options"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

AddedOct 26, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses draft-state persistence, a 1–3 minute latency expectation, the return payload (guide + edit URL), and the named failure mode insufficient_brief with a recovery protocol. That is exactly the behavioral context annotations cannot carry.

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?

Four short sentences, each carrying distinct information: purpose, latency, return value, error path, and scope limit. Front-loaded with the action and zero filler.

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?

For a generative, non-idempotent mutation tool the agent needs latency, output state, failure handling, and scope boundaries — all present, even though an output schema exists and return values would not have required explanation.

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 83%, so the schema already documents depth, objective, and the context fields; the description only loosely gestures at the brief contents ("research goals, discussion guide and intro") without mapping them to objective vs. researcherBriefing vs. productContext. Baseline 3 is appropriate given the schema does the heavy lifting.

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 first sentence gives a specific verb and resource ("Create an AI-moderated interview study from a brief") plus the concrete artifacts produced (research goals, discussion guide, intro) and their state (draft). This clearly separates it from the read-side siblings like get_interview_study and search_interview_transcripts.

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 states what the tool does not do ("No recruiting or launch"), which implicitly routes the agent to launch_test/audience tools for those steps, and gives a concrete retry procedure for the insufficient_brief case. It does not explicitly name an alternative sibling for the recruiting/launch path, so it falls short of a full 5.

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

All Uxia 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?