AssetLab

Create form template item

create_form_template_item

Add one question (item) to a form template. Build a form by calling this once per question in order, or use bulk_create on form-template-items. Requires form_template_items:write scope.

Input Schema

TableJSON Schema

Name	Required	Description
`label`	Yes	Question text / prompt shown to the user
`config`	No	Per-type settings. number: { min, max, unit, integer, decimals }. text: { multiline, maxLength, placeholder }. multi_select: { minSelections, maxSelections }. photo: { minPhotos, maxPhotos }.
`options`	No	REQUIRED for single_select/multi_select: at least 2 choices as { value, label } with unique values. value is a machine slug (e.g. "fail"), label is shown to the user (e.g. "Fail"). Omit for other types.
`item_key`	No	Optional stable key, unique within the template. OMIT IT and the server derives one from the label (recommended). Only set it when a later item’s visible_when must reference this one - then use a short slug like "compressor_status".
`required`	No	Whether an answer is required to complete the form (default false)
`help_text`	No	Optional hint shown under the label
`item_type`	Yes	Pick by the answer you want: single_select = exactly one choice (Pass/Fail, Yes/No, Yes/No/N-A, or custom - supply options); multi_select = pick several (supply options); number = a numeric reading/count (use config.min/max/unit/integer); checkbox = a single done/not-done tick; text = free comment (config.multiline for long text); photo = photo evidence (config.maxPhotos); section = a non-answerable heading that groups the questions under it.
`sort_order`	Yes	Display order within the template (0-based; questions render in this order)
`template_id`	Yes	Form template ID - resolve via list_form_templates
`visible_when`	No	Optional conditional visibility { itemKey, op, value }. itemKey must reference an EARLIER item’s key (set that item’s item_key explicitly). Operators by referenced type - single_select/checkbox: equals, not_equals, in, not_in, is_answered, is_blank; number: gt, lt, gte, lte, equals, not_equals, is_answered, is_blank; text: is_answered, is_blank, equals, not_equals; multi_select: in, not_in, is_answered, is_blank. e.g. show a "Details" text item only when item "compressor_status" equals "fail".

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 7, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare it is a non-read-only, non-destructive, non-idempotent, closed-world write. The description adds context beyond that: the required write scope ('form_template_items:write') and the ordering-sensitive per-item build pattern. It does not describe the returned payload, but there is no output schema to defer to.

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 that front-load the core action, then the workflow and alternative, then the auth requirement. No waste and no redundancy.

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?

Given 10 parameters with nested objects and a fully-documented schema but no output schema, the description covers purpose, workflow, alternative tool, and auth scope. It is nearly complete; only the shape of the return value is unaddressed, which is minor given the rich input schema.

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 fully documents the 10 parameters including the nested config, options, and visible_when structures. The description adds no parameter-level syntax or semantics beyond what the schema already provides, making the baseline 3 appropriate.

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?

The description uses a specific verb and resource ('Add one question (item) to a form template') and explicitly distinguishes this tool from the sibling alternative by naming bulk_create on form-template-items. An agent can tell what it does and how it differs from bulk creation without opening either 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?

It gives clear usage context ('call this once per question in order') and names the alternative (bulk_create). It stops short of stating when bulk is preferable to per-item calls, but the intended workflow is unambiguous.

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

All AssetLab 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?