Skip to main content
Glama

Conecto Forms

Create a form

forms_create

Create a form or survey with its own public page at https://cncto.co/f/, which anyone can open and answer; share that link. Field types: short_text, long_text, email, phone (default_country), url, number (min, max, integer), choice and multi_choice (options; multi_choice also min_selections, max_selections), rating (scale 3 to 10, default 5; low_label, high_label), nps (0 to 10; low_label, high_label), date (include_time for a time too, range for a first and a last day, earliest and latest as "2026-11-01" or "today", "today+7", "today-30"; answers read 2026-11-03, 2026-11-03T09:30, 2026-11-03/2026-11-07), yes_no, consent (a checkbox; its label may hold one link written text), statement (text only, no answer). Every field takes type, label, help, required, an id (generated from the label when left out; answers are keyed by it) and show_if {"field": "<an earlier field's id>", "equals": } to show it only when that answer was given. Each response received costs $0.01, up to 10,000 a month per account. Costs $0.01 per call; nothing if it fails.

Input Schema

NameRequiredDescriptionDefault
titleYes
fieldsYesThe questions in order. When changing a form, this replaces the whole list.
close_atNoStop taking responses at this time (ISO 8601, like 2026-12-31T23:59:00Z; UTC when no offset is given). Empty or null: never.
descriptionNoShown under the title.
on_responseNoWhat each response also does on its own, while you are away ($0.01 per action done): {"action": "open_ticket", "priority": "normal"} opens a help desk ticket for the respondent; {"action": "create_deal", "pipeline": "Sales", "stage": "New", "amount_field": "budget"} creates a deal with them as contact; {"action": "add_row", "table": "Leads", "columns": {"Email": "email", "Budget": "budget"}} adds a row, each column from a field id. [] or null: none.
save_to_crmNoSave the person behind each response as a CRM contact. The first email field is the email; a short_text field with id name or full_name (or first_name and last_name) is the name; the first phone field the phone. An existing contact only gets empty fields filled.
notify_emailNoEmail this address about new responses: at most one email a minute per form, later responses grouped into the next one. Empty or null: off.
redirect_urlNoAn https:// page to send people to after they submit. Empty or null: none.
submit_labelNoThe button's words (default "Submit").
hidden_fieldsNoLink values kept with each response: ["ref", "utm_source"] keeps them from https://cncto.co/f/<slug>?ref=abc&utm_source=newsletter.
max_responsesNoStop after this many responses. 0 or null: no limit.
thank_you_titleNoShown after sending (default "Thank you").
thank_you_messageNo
confirm_to_respondentNoEmail each respondent their answers in the brand kit (form_confirmation wording), to the address they typed in the first email field. $0.002 each; paid accounts only; at most three a day to one address.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

With annotations already declaring the safety profile (readOnly=false, destructive=false, idempotent=false), the description adds substantial context: per-call cost, per-response cost cap (10,000/month), on_response action pricing, and the rate-limited paid-only confirm_to_respondent. It stops short of describing the response object, but the economics and side effects are well disclosed.

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?

Purpose and URL are front-loaded, then field types and costs. It is long but dense; each clause carries real decision value. Some field-type detail overlaps the schema, keeping it just shy of a top score.

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 14-param creation tool with no output schema, it covers cost, side effects, and all field variants. It doesn't state what is returned (e.g., the form id/slug), which matters for actually sharing the link, but the rest is thorough.

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 86%, so the baseline is 3; the description goes further by synthesizing per-type rules (defaults, date formats, id generation from label, show_if semantics, slug-keyed answers) that help an agent chain fields correctly beyond isolated property docs.

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 ("Create a form or survey") plus the distinctive outcome (its own public page at a shareable slug URL). This clearly separates it from forms_update, forms_get, and forms_list without opening a schema.

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

Usage Guidelines3/5

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

The creation context is clear, but there is no explicit routing: nothing says to use forms_update for later edits or forms_get/forms_list to inspect an existing form. With siblings like forms_update and forms_delete present, the agent must infer when to pick this tool vs them.

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