Skip to main content
Glama

List forms

list_forms
Read-only

Every form in the workspace with its id, name, status (active, paused, draft or archived), Google output, Google Sheet link, submissions this month, when it last had delivery activity, what it does to its Sheet (operation insert adds rows; update and archive change or remove rows of the form named by targetFormId), whether Record Fetch is on, whether the rows of a form carry edit or remove links (recordLinksEnabled: a form that changes or removes rows puts them there itself, and a form that adds rows has them through the forms linked to it), how many submissions need review (needsReview: stopped for good and not marked reviewed - a delivery with another attempt scheduled is not counted) and how many are held for a website not yet allowed (heldSubmissions). The console shows each form that adds rows as a Connection, with the forms whose targetFormId names it linked to it as its edit and remove abilities; a Connection reads Paused when its form is paused and Needs review when needsReview or heldSubmissions is above zero. share_url is the address of the form's public Webtzm page while that page is on, otherwise null.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_forms"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
formsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / forms / items / properties / share_url / description
      Previous value: -"The form's public page address while the page is on (the custom address when a Pro workspace has set one), otherwise null."New value: +"The form's public page address, a short link that stays the same for good, while the page is on, otherwise null."
  2. Changed1 schema field changed
    • addedOutput schema / properties / forms / items / properties / share_url
      Added value: +{
      +  "description": "The form's public page address while the page is on (the custom address when a Pro workspace has set one), otherwise null.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  3. Changed4 schema fields changed
    • addedOutput schema / properties / forms / items / properties / operation
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / forms / items / properties / recordFetchEnabled
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / forms / items / properties / recordLinksEnabled
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / forms / items / properties / targetFormId
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  4. First observed

TDQS

B3.3/5.0
Behavior4/5

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

The annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety needs no restating. Beyond that, the description adds genuine semantics the annotations cannot carry: status values, the null condition for share_url, why a scheduled retry does not count toward needsReview, and how heldSubmissions differs from needsReview. It loses a point because a term like 'Google output' is left undefined and the framing of Connections versus forms is only half explained.

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

Conciseness2/5

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

The entire definition is one unbroken ~200-word sentence with no front-loaded summary or structure, forcing the agent to parse field semantics out of a run-on clause chain. Much of that field-by-field detail duplicates what the existing output schema already supplies.

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

Completeness3/5

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

With zero parameters, read-only annotations and an output schema already provided, the description is more than complete on the return side. It is nonetheless incomplete where it matters more: nothing tells the agent when to choose this over get_form or get_workspace, so the caller still has to guess at routing.

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?

This tool takes no parameters, so there is no parameter meaning to add and the baseline applies. The description correctly spends no words on inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause 'Every form in the workspace with its id, name, status...' gives a specific verb (list) and resource (forms) with full scope. It does not name or distinguish itself from the obvious sibling get_form, so the agent must infer that this is the enumerate-all variant rather than the single-form fetch.

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

Usage Guidelines2/5

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

There is no when-to-use statement, no exclusion and no pointer to an alternative such as get_form for a single form. Usage is only implied by the word 'Every', which suggests enumeration but says nothing about when a different tool is the right choice.

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