Skip to main content
Glama

Create Forms survey

forms_surveys_create

Create a new form from provided settings and return its Survey ID. Add questions next, then publish to make it fillable.

Instructions

Create a new form from the given settings; returns the created Survey (note its id).

Only the fields you set are sent. Follow up with questions_create to add questions and surveys_publish to make the form fillable.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyYesTyped request body for creating a form (``POST /surveys``). Every setting the API publishes is a field. The CLI has an option for the common ones; the rest are set with its common ``-F key=value`` and ``--body-file``. Unset (``None``) fields are dropped before the request is sent. ``language``, ``is_published`` and ``is_public`` are accepted and ignored by the API (checked live on 2026-10-04): they stay for callers that send them, and setting one logs a warning.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.122.1
    • changedInput schema / properties / body / description
      Previous value: -"Typed request body for creating a form (``POST /surveys``).\n\nEvery setting the API publishes is a field. The CLI has an option for the common ones and\ntakes the rest through its repeatable ``--field key=value`` JSON escape, merged onto this\nbody. Unset (``None``) fields are dropped before the request is sent. ``language``,\n``is_published`` and ``is_public`` are accepted and ignored by the API (checked live on\n2026-10-04): they stay for callers that send them, and setting one logs a warning."New value: +"Typed request body for creating a form (``POST /surveys``).\n\nEvery setting the API publishes is a field. The CLI has an option for the common ones; the\nrest are set with its common ``-F key=value`` and ``--body-file``. Unset (``None``) fields\nare dropped before the request is sent. ``language``, ``is_published`` and ``is_public``\nare accepted and ignored by the API (checked live on 2026-10-04): they stay for callers\nthat send them, and setting one logs a warning."
    • changedInput schema / properties / body / properties / api_keys / anyOf
      Previous value: -[
      -  {
      -    "items": {
      -      "additionalProperties": false,
      -      "description": "An API key a form's integrations use (``api_keys`` item of a request).",
      -      "properties": {
      -        "id": {
      -          "anyOf": [
      -            {
      -              "type": "string"
      -            },
      -            {
      -              "type": "null"
      -            }
      -          ],
      -          "default": null,
      -          "description": "Id of an existing key."
      -        },
      -        "name": {
      -          "description": "Name of the key.",
      -          "type": "string"
      -        },
      -        "secure": {
      -          "anyOf": [
      -            {
      -              "type": "boolean"
      -            },
      -            {
      -              "type": "null"
      -            }
      -          ],
      -          "default": null,
      -          "description": "Whether the value is stored encrypted (the API's default)."
      -        },
      -        "value": {
      -          "anyOf": [
      -            {
      -              "type": "string"
      -            },
      -            {
      -              "type": "null"
      -            }
      -          ],
      -          "default": null,
      -          "description": "Value of the key."
      -        }
      -      },
      -      "required": [
      -        "name"
      -      ],
      -      "type": "object"
      -    },
      -    "type": "array"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "items": {
      +      "additionalProperties": false,
      +      "description": "An API key a form's integrations use (``api_keys`` item of a request).",
      +      "properties": {
      +        "id": {
      +          "anyOf": [
      +            {
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "description": "Id of an existing key."
      +        },
      +        "name": {
      +          "description": "Name of the key.",
      +          "type": "string"
      +        },
      +        "secure": {
      +          "anyOf": [
      +            {
      +              "type": "boolean"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "description": "Whether the value is stored encrypted (the API's default)."
      +        },
      +        "value": {
      +          "anyOf": [
      +            {
      +              "format": "password",
      +              "type": "string",
      +              "writeOnly": true
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "description": "Value of the key: a secret, sent and never printed."
      +        }
      +      },
      +      "required": [
      +        "name"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. First observedv0.67.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly=false, destructive=false, idempotent=false, and openWorld=true, so the safety profile is covered structurally. The description adds genuinely new behavior: partial-send semantics ("only the fields you set are sent") and the fact that the created Survey object with its id is returned. No auth or permission requirements are stated, keeping it out of 5.

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 sentences and one parenthetical, front-loaded with the core action and return value, with no redundant restatement of the name or annotations.

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 one-param, deeply nested create tool with no output schema, the description covers what is returned (the Survey and its id) and the partial-send behavior. The workflow handoff to questions_create and surveys_publish makes it usable end-to-end, though it does not warn about the ignored fields (language, is_published, is_public) documented in the 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% and the single nested body param is exhaustively documented, so the baseline is 3. The description's "only the fields you set are sent" reinforces the partial-send behavior but adds no field-level syntax or defaults beyond what the schema already provides.

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 new form") and immediately distinguishes itself from the sibling tool that would otherwise be confused for creation work by routing to questions_create and surveys_publish. An agent can identify the tool's role without opening the 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?

Explicitly names the two follow-up tools and the condition that selects them (add questions, make fillable), which gives clear workflow context. It does not state when NOT to use this tool (e.g. clone vs create), so it stops short of full when/when-not/alternatives coverage.

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

Deploy Server

Other Tools