Skip to main content
Glama

Make a form

create_form

Make a form as a tracked link (a lead intake, a quote request, an RSVP, feedback, an application) and get its URL. Readers fill it on the link; the user sees every response, where people stop filling it, the time on each question and a replay of how each person filled it, and gets an email for each one sent. mode conversation: an AI asks the questions and fills the form from what the reader says (0.2 cents per AI reply, from the user's free AI first, then AI credits). Ask only what is needed; group questions into parts only when it helps.

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": {
      "title": "<title>",
      "questions": "<questions>"
    },
    "name": "create_form"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoform (default): a classic form, one part at a time. conversation: AI asks the questions in a chat.
allowNoOnly these emails or domains can open it, e.g. ["@sequoiacap.com", "dana@acme.com"].
introNoOne or two sentences under the title.
limitNoStop taking responses after this many are sent.
titleYes
accessNopublic: anyone with the link. email: reader types an email (fake and throwaway addresses are refused). verified: reader proves the email, with Google or a 6-digit email code.
folderNoPut it in this folder on my Files page, by name. Made if it does not exist. Leave out to keep it outside folders.
notifyNoEmail me when someone opens it the first time. Default true.
thanksNoWhat the reader sees after sending it.
close_onNoStop taking responses after this day, YYYY-MM-DD (Pacific).
downloadsNoReaders get a Download button for a PDF, Office file, image or video. Default false.
questionsYes
ai_readingNoWhat a reader's own AI (Claude, ChatGPT) may take. questions (default): only the parts that answer each question, so I see every question and no full copy leaves. full: the whole text, marked with the reader's email. off: no AI reading.
expires_in_daysNoClose the link after this many days.
discourage_screenshotsNoBlur the page when the reader switches away, block printing and copying, and watermark it with their email. No website can fully stop a screenshot. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only flag it as a non-destructive, open-world write, but the description adds real behavioral context: readers fill the link, the owner receives an email per response, analytics (drop-off, per-question time, replay) are captured, and conversation mode costs 0.2 cents per AI reply drawn from free AI then credits. It still leaves auth requirements and failure behavior unstated, so not a 5.

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?

Front-loaded with the core action and result, and every clause carries information about outcomes or cost. The middle sentence is a long, dense run-on bundling analytics, email notification, and fill behavior, which slightly hurts scannability but wastes no words outright.

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 15-parameter creation tool with no output schema, the description supplies the missing return value (the URL) plus side effects (email notifications, analytics, per-reply cost) that an agent must know before invoking. Remaining gaps are modest given the high schema coverage.

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 already 87%, so the baseline is 3; the description earns an extra point by adding meaning to 'mode' that the enum text does not carry (AI-driven questioning plus its pricing model) and by advising on the 'part' grouping parameter. Other 15 params, such as access, notify, and downloads, get their semantics from the schema rather than the description.

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 — 'Make a form as a tracked link' — plus the concrete outcome ('get its URL') and example use cases (lead intake, RSVP, application). This clearly separates it from siblings like form_responses, which consume what a form produces.

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 clear contextual guidance for choosing between mode 'form' (classic, one part at a time) and 'conversation' (AI asks in chat, with a cost tradeoff stated), and closes with design advice ('Ask only what is needed; group questions into parts only when it helps'). It stops short of naming when not to use it or pointing to siblings for reading responses or managing existing links.

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