edit_question
Create, update, move, or configure a question in a standard block, or Content (informational_block) in an End of Survey block. Use create without question_id; use configuration with get_mcp_schema for type-specific fields. To remove one, use delete_question instead.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "edit_question"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Variable name used for piping ({{answer:name}}) and export column names, e.g. favorite_movie | |
| title | No | New question prompt text | |
| create | No | Create a question in a standard block, or Content (informational_block) in an End of Survey block (omit question_id) | |
| hidden | No | Hide or show in the respondent survey | |
| block_id | No | Move question to this block (standard, or end_survey when the question is Content) | |
| honeypot | No | Beta (needs beta-tester access to turn on; anyone can turn it off). Make this a honeypot (question Options → Fraud Detection → Honeypot): the survey keeps it in the page for bots but hides it from people — not visible, not focusable, not read by screen readers — and never requires, numbers, or counts it as missing. It catches naive fill-every-field automation; visibility-aware bots can skip it and autofill can trigger it, so any answer adds a warning (honeypot_triggered) to Quality Review and the combined Quality Score, never an automatic exclusion. It never blocks a submission. Trap contents are discarded; exports retain only an answered/redacted status. Only short_answer, multiple_choice, grid_matrix, slider, constant_sum, and max_diff questions (other types are either skipped by form-filling bots or act on their own while hidden). Silicon Sample leaves honeypots blank. Read back as honeypot in read_question. | |
| position | No | 0-based position within the current block | |
| required | No | optional, requested (respondents are asked to answer but may skip), or required | |
| skip_rules | No | Add, update, or delete per-question Skip Rules, or toggle the per-option editor affordance. | |
| custom_code | No | Custom HTML/JS injected for this question. | |
| question_id | No | Question UUID (omit for bulk_order_mode-only edits or create) | |
| configuration | No | Type-specific configuration patch for an existing question | |
| agent_only_mode | No | Beta agent-signal mode. off removes the feature; custom_text delivers agent_only_text without scoring; generated_canary randomly offers a per-response code and dedicated non-substantive field, then stores only derived assignment/completion/match evidence. Read back as agent_only_mode. | |
| agent_only_text | No | Beta (needs beta-tester access to set non-empty text; pass an empty string to clear). Plain text appended to this question in the respondent page DOM but hidden visually, unfocusable, and excluded from the accessibility tree. Use it for researcher-authored instructions or canaries aimed at agents that ingest HTML or extracted page text. Screenshot-only agents will not see it, and anyone inspecting page source can, so it is neither secret nor a standalone detector. No HTML or JavaScript is interpreted. Do not ask an agent to expose credentials, private context, or system prompts. Read back as agent_only_text in read_question. | |
| bulk_order_mode | No | Apply the same shuffle setting to all questions of a type across a survey or block. | |
| followup_trigger | No | Follow-up trigger fields — use get_mcp_schema module=question kind=followup_trigger | |
| page_break_after | No | Start a new page after this question | |
| reorder_in_block | No | Replace question order in a block (works on its own, without question_id) | |
| parent_question_id | No | Parent for follow-up linkage, or null to detach | |
| restore_from_trash | No | Restore one recoverable question (and nested follow-ups) from survey trash | |
| agent_canary_sample_percent | No | For generated_canary, the percentage of responses randomly offered the canary; the remainder are controls. Defaults to 100. Raw codes and entered canary text are discarded before storage. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |