Skip to main content
Glama

forms.forms.watches.create

Creates a watch on a Google Form to notify you of schema or response events; each watch expires after seven days and must be unique per form and event type.

Instructions

Create a new watch. If a watch ID is provided, it must be unused. For each invoking project, the per form limit is one watch per Watch.EventType. A watch expires seven days after it is created (see Watch.expire_time) [HTTP POST] — creates or triggers a change; refused under --readonly safety profiles. Returns the API's response resource as JSON — request body is a JSON CreateWatchRequest object accepting watch, watchId; pass it via params or whole via body_file Siblings over the same resource: delete, list, renew.

Input Schema

NameRequiredDescriptionDefault
queryNoExtra KEY=VALUE query pairs for endpoints whose parameters Discovery does not describe.
formIdYes[URL path segment] Required. ID of the Form to watch.
paramsNoParameter map merged into the request; typed parameters win.
dry_runNoReturn the request that would be sent, without sending it.
body_fileNoRead the request body from this file ('-' for stdin) instead of building one from the parameters. The body is a JSON CreateWatchRequest object.
request_bodyNoRequest body of type CreateWatchRequest: pass it via `params` (merged into the built body) or whole via `body_file`.

Output Schema

NameRequiredDescriptionDefault
idNo
stateNo
targetNo
errorTypeNo
eventTypeNo
createTimeNo
expireTimeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / body_file / description
      Previous value: -"Read the request body from this file ('-' for stdin) instead of building one from the parameters."New value: +"Read the request body from this file ('-' for stdin) instead of building one from the parameters. The body is a JSON CreateWatchRequest object."
    • addedInput schema / properties / request_body
      Added value: +{
      +  "description": "Request body of type CreateWatchRequest: pass it via `params` (merged into the built body) or whole via `body_file`.",
      +  "properties": {
      +    "watch": {
      +      "properties": {
      +        "createTime": {
      +          "type": "string"
      +        },
      +        "errorType": {
      +          "enum": [
      +            "ERROR_TYPE_UNSPECIFIED",
      +            "PROJECT_NOT_AUTHORIZED",
      +            "NO_USER_ACCESS",
      +            "OTHER_ERRORS"
      +          ],
      +          "type": "string"
      +        },
      +        "eventType": {
      +          "enum": [
      +            "EVENT_TYPE_UNSPECIFIED",
      +            "SCHEMA",
      +            "RESPONSES"
      +          ],
      +          "type": "string"
      +        },
      +        "expireTime": {
      +          "type": "string"
      +        },
      +        "id": {
      +          "type": "string"
      +        },
      +        "state": {
      +          "enum": [
      +            "STATE_UNSPECIFIED",
      +            "ACTIVE",
      +            "SUSPENDED"
      +          ],
      +          "type": "string"
      +        },
      +        "target": {
      +          "properties": {
      +            "topic": {
      +              "properties": {
      +                "topicName": {
      +                  "type": "string"
      +                }
      +              },
      +              "type": "object"
      +            }
      +          },
      +          "type": "object"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "watchId": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / formId / description
      Previous value: -"Required. ID of the Form to watch."New value: +"[URL path segment] Required. ID of the Form to watch."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "createTime": {
      +      "type": "string"
      +    },
      +    "errorType": {
      +      "enum": [
      +        "ERROR_TYPE_UNSPECIFIED",
      +        "PROJECT_NOT_AUTHORIZED",
      +        "NO_USER_ACCESS",
      +        "OTHER_ERRORS"
      +      ],
      +      "type": "string"
      +    },
      +    "eventType": {
      +      "enum": [
      +        "EVENT_TYPE_UNSPECIFIED",
      +        "SCHEMA",
      +        "RESPONSES"
      +      ],
      +      "type": "string"
      +    },
      +    "expireTime": {
      +      "type": "string"
      +    },
      +    "id": {
      +      "type": "string"
      +    },
      +    "state": {
      +      "enum": [
      +        "STATE_UNSPECIFIED",
      +        "ACTIVE",
      +        "SUSPENDED"
      +      ],
      +      "type": "string"
      +    },
      +    "target": {
      +      "properties": {
      +        "topic": {
      +          "properties": {
      +            "topicName": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        }
      +      },
      +      "type": "object"
      +    }
      +  },
      +  "type": "object"
      +}
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it discloses that this is a mutating POST, refused under --readonly profiles, subject to quotas, and returns the created resource as JSON. It omits auth requirements and error handling, keeping it from 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?

The purpose is front-loaded in the first sentence, and subsequent sentences add constraints and routing hints. Some details (e.g., repeating body format from the schema) could be trimmed, but the information is organized and generally earns its place.

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?

Given a complex mutation tool with nested objects, an output schema, and no annotations, the description covers purpose, constraints, expiration, safety-profile refusal, and body/return shape. It leaves out permission and error specifics, but it is sufficient for an agent to invoke correctly.

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?

The schema coverage is 100%, so a baseline of 3 applies. The description adds meaningful nuance: it specifies that a provided watch ID must be unused and that the request body (CreateWatchRequest with watch, watchId) can be passed via params or body_file, going beyond the schema's field-level descriptions.

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 description opens with 'Create a new watch', a specific verb plus resource, and it names sibling operations (delete, list, renew) at the end. It stops short of explicitly differentiating when to use each sibling, so it earns a 4 rather than a 5.

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?

It supplies constraints (unused watch ID, one watch per event type per project, seven-day expiry) and lists sibling tools, which implies context. However, it never states explicitly when to choose create over renew or delete, so the usage guidance remains implied rather than direct.

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