Paperform

Create item

create

Create an item or a record. Fields are passed through as given and checked by the product, so read the item first and send the field names it reports; an unknown or malformed field comes back as an error naming it.

By type: • form — a new form in space_id. body is its source in the form source dialect (read get_help topic "forms" first); omitted, the form starts empty. title names it. folder is an @platform folder id from list (omitted: the top of the space). slug is not taken here: write slug in the body's frontmatter, or set custom_slug with update afterwards. • folder — title names it; parent is the folder it goes in. It holds documents and workflows; with no parent it goes at the top of the space. • document — from a template or another document: from is its id. With fields (participants, prefill, …) a draft is made from it; with only title it is copied. folder places the result. Nothing is sent: send_document is its own step. • workflow — a new draft workflow in space_id (or folder). title names it; body is an initial definition in the workflow dialect (get_help topic "workflow"). Nothing runs until publish. • product, coupon — on a Paperform form: parent is the form id, fields the record (a product needs its products field's key and an upper-case SKU; a coupon its code and discountPercentage or discountAmount). • form_webhook — on a Paperform form (parent): fields.target_url receives every submission, personal details included. Confirm with the user before calling this. • document_webhook — on a folder (parent): fields.url receives signing events, participant emails included. Confirm with the user before calling this.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "<type>"
    },
    "name": "create"
  }
}

Input Schema

Name	Required	Description
`body`	No	The initial source: the form source dialect for a form (get_help topic "forms"), or the workflow dialect for a workflow (get_help topic "workflow"). Omitted, a valid starter is used.
`from`	No	Documents: the template or document id to start from.
`slug`	No	Not taken here: write slug in the form source frontmatter.
`type`	Yes	What to create.
`title`	No	The new item's name.
`fields`	No	The record's fields, as the product names them.
`folder`	No	The folder id to put it in: an @platform folder from list.
`parent`	No	The id the new record belongs to (a form, a folder).
`message`	No	Not used here; leave it out.
`space_id`	No	The space to act in — a key of whoami's `spaces`. Not needed when another argument already carries an id from that space, or when this connection reaches only one space.

Output Schema

Name	Required	Description	Default
`id`	No
`url`	No
`title`	No
`record`	No
`dry_run`	No
`diagnostics`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare it non-readonly, non-destructive and non-idempotent, and the description adds substantial context beyond that: fields are validated by the product with errors naming the bad field, omitted body yields a valid starter, workflow drafts do not run until publish, and webhooks exfiltrate personal details and therefore need user confirmation. Those are exactly the side effects an agent needs before mutating state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The lead sentence front-loads the core rule (pass-through + validate-by-reading-first), and the per-type bullets make a long description scannable. It is longer than most definitions but nearly every clause carries operational information; some per-type lines restate the schema descriptions and could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a ten-parameter, eight-variant creation tool with an output schema available, the description covers every variant, the schema-dialect dependencies, the id-provenance rules, and the confirmation requirements. Nothing needed to call it correctly across its branches appears to be missing.

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 coverage is 100%, so the schema alone documents each parameter, but the description adds cross-parameter conditional meaning the flat schema cannot express — which of space_id, folder, parent, body and fields apply to each of the eight types. It also preempts misuse by noting slug is not taken here and message is unused.

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 first sentence gives a specific verb and resource ('Create an item or a record') and the per-type breakdown enumerates exactly which resources are creatable. It actively distinguishes from siblings by naming send_document ('Nothing is sent: send_document is its own step') and update ('set custom_slug with update afterwards'), so an agent can route correctly without opening another schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage guidance is explicit per type: read get_help topic "forms" or "workflow" before supplying body, use from for document copies vs drafts, and confirm with the user before calling form_webhook or document_webhook. Prerequisites and hand-offs to update and send_document are stated outright.

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

All Paperform 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?