Skip to main content
Glama

Formstep

by io.github.formstep
OverviewDiscussionsAdmin

Insert decision question

editor_insertDecisionQuestion

Insert the decision question (approve / decline / request changes) that sets a request's outcome. A plain radio never sets an outcome.

Input Schema

NameRequiredDescriptionDefault
afterNoNodeId to insert after. Use $prev to chain. Omitting appends to end (usually wrong).
titleYesQuestion title in the form language, e.g. "Do you approve?"
formIdYesForm ID to insert into
labelsYesOption labels in the form language, e.g. { approve: "Approve", decline: "Decline", changes: "Request changes" }
isHiddenNoStart hidden (the target of a `show` rule).
parentIdNoParent node ID to insert into (e.g., column1)
positionNoPosition among siblings: inside parentId when given, else at the top level ('first' = top of the form, e.g. a title). Not combinable with after.
requiredNoDefault: true

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / labels / description
      Previous value: -"Option labels in the form language"New value: +"Option labels in the form language, e.g. { approve: \"Approve\", decline: \"Decline\", changes: \"Request changes\" }"
    • addedInput schema / properties / labels / required
      Added value: +[
+  "approve",
+  "decline",
+  "changes"
+]
    • changedInput schema / properties / title / description
      Previous value: -"Default: \"Do you approve?\""New value: +"Question title in the form language, e.g. \"Do you approve?\""
    • changedInput schema / required
      Previous value: -[
-  "formId"
-]New value: +[
+  "formId",
+  "title",
+  "labels"
+]
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already disclose the safe-mutation profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds a genuine behavioral fact the annotations cannot: this element is what actually sets a request's outcome, which matters for choosing it. It does not cover revert/positioning side effects, which the schema handles.

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?

Two tightly written sentences, front-loaded with the action and the distinguishing semantic, with zero filler. The radio contrast is placed last as a routing hint.

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 no output schema, the description conveys the essential semantic (outcome-setting decision question) and the schema carries the rich positional/nesting detail at 100% coverage. It lacks guidance on placement or chaining, but the schema's after/position descriptions cover that.

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 description coverage is 100%, so the schema already documents all 8 parameters, including the labels object and the after/position chaining rules. The description adds no parameter detail beyond restating the label values, so the baseline of 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 and resource ('Insert the decision question ... that sets a request's outcome') and nails the disambiguating trait of the three option labels (approve/decline/changes). It implicitly separates itself from editor_insertRadioQuestion by noting a plain radio never sets an outcome.

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?

The clause 'A plain radio never sets an outcome' tells the agent when this tool is the right choice over the radio-question sibling, which is the key routing decision among the many insert_* tools. It stops short of an explicit 'use X instead' or stating prerequisites, so it is clear context without full exclusions.

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

All Formstep toolsInspect
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