Uxia

Set Survey

set_survey

Destructive

Add or replace a Survey block’s questions. Omit blockId to append with a server-assigned ID, or use an existing Survey ID to edit. Returns blockId for new surveys. Other blocks are preserved. No launch.

Input Schema

TableJSON Schema

Name	Required	Description
`testId`	Yes
`blockId`	No	Omit to append a new survey with a server-assigned ID. Supply an existing survey ID to edit.
`questions`	Yes	Follow-up survey questions capture judgments, comparisons, friction and what the researcher wants to learn. Use explicit question objects with unique id, type, question and required fields. open_ended needs question text; multiple_choice, ranking and budget_allocation need at least two non-empty options. allowMultiple applies to multiple_choice. rating needs scaleMin < scaleMax; rating and ranking require scaleLabels.min and scaleLabels.max naming the endpoints. budget_allocation asks testers to split 100 points across options. yes_no asks for a yes/no answer. At most 10 questions per Survey; launch preview reports plan and test-wide limits.
`expectedRevision`	No	Legacy compatibility only; ignored. Draft revisions are resolved automatically.

Output Schema

TableJSON Schema

Name	Required	Description
`url`	No	Open the draft in Uxia.
`testId`	No
`blockId`	No	Server-assigned ID of the added block. Use it for subsequent edits and references.
`editable`	No
`definition`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 2, 2026

addedInput schema / properties / expectedRevision / description

Added value: +"Legacy compatibility only; ignored. Draft revisions are resolved automatically."

changedInput schema / required

Previous value: -[
-  "testId",
-  "expectedRevision",
-  "questions"
-]New value: +[
+  "testId",
+  "questions"
+]

Changed4 schema fields changedOct 1, 2026

addedInput schema / properties / blockId / description

Added value: +"Omit to append a new survey with a server-assigned ID. Supply an existing survey ID to edit."

addedInput schema / properties / questions / description

Added value: +"Follow-up survey questions capture judgments, comparisons, friction and what the researcher wants to learn. Use explicit question objects with unique id, type, question and required fields. open_ended needs question text; multiple_choice, ranking and budget_allocation need at least two non-empty options. allowMultiple applies to multiple_choice. rating needs scaleMin < scaleMax; rating and ranking require scaleLabels.min and scaleLabels.max naming the endpoints. budget_allocation asks testers to split 100 points across options. yes_no asks for a yes/no answer. At most 10 questions per Survey; launch preview reports plan and test-wide limits."

changedInput schema / required

Previous value: -[
-  "testId",
-  "expectedRevision",
-  "blockId",
-  "questions"
-]New value: +[
+  "testId",
+  "expectedRevision",
+  "questions"
+]

addedOutput schema / properties / blockId

Added value: +{
+  "description": "Server-assigned ID of the added block. Use it for subsequent edits and references.",
+  "type": "string"
+}

First observedSep 28, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false. The description adds genuinely useful context beyond them: mutations are scoped ('Other blocks are preserved'), new surveys receive a server-assigned ID returned as blockId, and no launch is triggered. It stops short of stating that existing questions in the block are overwritten, which is the main destructive consequence.

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?

Three short sentences, no filler, with the primary action stated first and the blockId append-vs-edit rule front-loaded. Every clause carries information.

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 mutation tool with a rich input schema and an existing output schema, the description covers the key decisions: append vs edit, preservation of other blocks, and no launch. Return values need no explanation thanks to the output schema. Minor gap: it never warns that supplied questions replace the block's current contents.

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 75% and the questions sub-schema already documents types, options, scale labels, image shapes and the 10-question cap in detail. The description's blockId guidance duplicates the schema's own description text and says nothing about expectedRevision, so it adds little beyond structured data. 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?

States a specific verb+resource: add or replace a Survey block's questions. This is clearly distinct from siblings like add_test_block and update_test_block, and the scope ('Survey block's questions') is precise enough for an agent to select it without opening the schema.

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?

Explicitly routes the two modes: omit blockId to append, supply an existing Survey ID to edit. It also rules out the launch step with 'No launch.' It does not, however, compare against adjacent tools such as preview_test_launch or update_test_block, so the when-not guidance is incomplete.

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?