Skip to main content
Glama

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

NameRequiredDescriptionDefault
nameNoVariable name used for piping ({{answer:name}}) and export column names, e.g. favorite_movie
titleNoNew question prompt text
createNoCreate a question in a standard block, or Content (informational_block) in an End of Survey block (omit question_id)
hiddenNoHide or show in the respondent survey
block_idNoMove question to this block (standard, or end_survey when the question is Content)
honeypotNoBeta (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.
positionNo0-based position within the current block
requiredNooptional, requested (respondents are asked to answer but may skip), or required
skip_rulesNoAdd, update, or delete per-question Skip Rules, or toggle the per-option editor affordance.
custom_codeNoCustom HTML/JS injected for this question.
question_idNoQuestion UUID (omit for bulk_order_mode-only edits or create)
configurationNoType-specific configuration patch for an existing question
agent_only_modeNoBeta 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_textNoBeta (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_modeNoApply the same shuffle setting to all questions of a type across a survey or block.
followup_triggerNoFollow-up trigger fields — use get_mcp_schema module=question kind=followup_trigger
page_break_afterNoStart a new page after this question
reorder_in_blockNoReplace question order in a block (works on its own, without question_id)
parent_question_idNoParent for follow-up linkage, or null to detach
restore_from_trashNoRestore one recoverable question (and nested follow-ups) from survey trash
agent_canary_sample_percentNoFor 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

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the bar is lower, and the description is consistent with them — removal is routed elsewhere. What it does not add is behavior the annotations can't convey: whether edits are reversible, that restore_from_trash implies a recoverable trash, or that bulk_order_mode mutates every question of a type survey-wide. The rich behavioral detail (honeypot side effects, canary storage) lives in the schema, not the description.

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 sentences, front-loaded with the verb set and the informational_block carve-out, then the mode-selection rule, then the exclusion. No filler and no restatement of the tool name.

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?

For a mutation tool this large — 21 parameters, nested objects, skip rules, custom JS/HTML, bulk ordering, trash restore, honeypot and canary modes — the description covers only the create/update/move/configure core. An output schema exists so return values need no explanation, and the schema documents the omitted modes well, but an agent selecting among siblings would not learn from the description that this tool can reorder a whole survey or restore a trashed question.

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

Parameters4/5

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

Schema description coverage is 100% and every one of the 21 parameters is documented, so the baseline is 3. The description earns above baseline by explaining the modality that the schema cannot: with zero required parameters, the create / question_id split is the whole dispatch mechanism, and the description states it directly along with the get_mcp_schema handoff for configuration patches.

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?

Names four specific verbs (create, update, move, configure) plus the resource, and adds a domain nuance most agents would miss: 'Content' is an informational_block living in an End of Survey block rather than a standard block. It also explicitly names the sibling it is not (delete_question). It falls short of 5 because several real capabilities of this tool — bulk_order_mode reordering, restore_from_trash, reorder_in_block — are entirely absent from the stated purpose.

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?

Gives two decisive routing rules that would otherwise require reading a 21-parameter schema: omit question_id to create, pair configuration with get_mcp_schema for type-specific fields. It also names the correct alternative for removal (delete_question). It does not say when to reach for bulk_order_mode or restore_from_trash instead of per-question edits, so guidance is clear but not exhaustive.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources