Uxia

Create Audience

create_audience

Create a new audience in the caller's Uxia workspace and synchronously generate AI testers for it. An audience defines targeting filters (age, gender, geography, demographics) used to generate synthetic AI tester profiles, not recruit people. Returns the created audience plus the freshly generated testers.

Input Schema

Name	Required	Description
`name`	No
`count`	No	How many AI testers to generate. Defaults to 5, which is the minimum a test can launch with — an audience with fewer approved testers is rejected at launch.
`roles`	No
`gender`	Yes
`ageRange`	Yes	Two-element [min, max] age range (integers, 16-100).
`countries`	No	Country of residence codes in uppercase ISO 3166-1 alpha-2 format. Use KR for South Korea, US for United States, GB for United Kingdom; do not send country names.
`languages`	No
`industries`	No
`isReusable`	No
`description`	No
`techLiteracy`	No
`customDetails`	No
`maritalStatus`	No
`nationalities`	No	Nationality country codes in uppercase ISO 3166-1 alpha-2 format. Use KR for South Korean, US for American, GB for British; do not send nationality names.
`educationLevel`	No
`personalIncome`	No
`householdIncome`	No
`employmentStatus`	No
`languagesRequirement`	No

Output Schema

Name	Required	Description	Default
`testers`	No	Freshly generated AI testers for the new audience.
`audience`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 4, 2026

addedInput schema / properties / countries / description

Added value: +"Country of residence codes in uppercase ISO 3166-1 alpha-2 format. Use KR for South Korea, US for United States, GB for United Kingdom; do not send country names."

addedInput schema / properties / countries / items / pattern
```
Added value: +"^[A-Z]{2}$"
```

addedInput schema / properties / nationalities / description

Added value: +"Nationality country codes in uppercase ISO 3166-1 alpha-2 format. Use KR for South Korean, US for American, GB for British; do not send nationality names."

addedInput schema / properties / nationalities / items / pattern
```
Added value: +"^[A-Z]{2}$"
```

Changed3 schema fields changedOct 15, 2026
- changedInput schema / properties / ageRange / description
```
Previous value: -"Two-element [min, max] age range (integers, 0-120)."New value: +"Two-element [min, max] age range (integers, 16-100)."
```
- changedInput schema / properties / ageRange / items / maximum
```
Previous value: -120New value: +100
```
- changedInput schema / properties / ageRange / items / minimum
```
Previous value: -0New value: +16
```
Changed6 schema fields changedSep 30, 2026
- removedInput schema / properties / personalIncome / properties / range / $ref
```
Removed value: -"#/properties/householdIncome/properties/range"
```
- addedInput schema / properties / personalIncome / properties / range / description
```
Added value: +"Two-element [min, max] range in the given currency."
```
- addedInput schema / properties / personalIncome / properties / range / items
```
Added value: +{
+  "maximum": 500000,
+  "minimum": 0,
+  "type": "number"
+}
```
- addedInput schema / properties / personalIncome / properties / range / maxItems
```
Added value: +2
```
- addedInput schema / properties / personalIncome / properties / range / minItems
```
Added value: +2
```
- addedInput schema / properties / personalIncome / properties / range / type
```
Added value: +"array"
```
First observedSep 28, 2026

TDQS

B3.4/5.0

Behavior4/5

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

Annotations already flag this as a non-readonly, non-idempotent, non-destructive creation, so the bar is lower. The description still earns credit by disclosing the synchronous tester-generation side effect (implying latency and cost) and the return payload ('created audience plus the freshly generated testers'), which annotations alone would not reveal.

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 tight, front-loaded sentences with no filler; the 'not recruit people' clarification earns its place by preventing a plausible misinterpretation. It could have spent a clause or two on the required ageRange/gender constraints instead, but nothing is bloated.

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?

An output schema exists and the description sensibly summarizes the return value. However, for a 19-parameter non-idempotent mutation with synchronous generation, it omits duplicate-audience risk, credit consumption, and the meaning of most filter fields, so an agent is only partially equipped to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 19 parameters and only 21% schema description coverage, the description must compensate and largely does not. It names broad filter categories (age, gender, geography, demographics) but says nothing about semantics of roles, industries, techLiteracy, customDetails, educationLevel, income objects, employmentStatus, languagesRequirement, or isReusable, leaving most parameters opaque without external documentation.

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?

States a specific verb and resource ('Create a new audience in the caller's Uxia workspace') and adds a critical semantic clarification: it synchronously generates synthetic AI tester profiles rather than recruiting real people. That distinguishes it conceptually from list_audiences/get_audience/set_test_audience, though no sibling is named explicitly.

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?

Usage is implied rather than stated: it creates an audience and immediately generates testers, so an agent can infer it is the entry point before set_test_audience/launch_test. There is no explicit when-to-use vs when-not guidance, and nothing about creating multiple audiences versus reusing one via isReusable.

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?