grr

Overview Schema Source Related Servers Discussions Admin

drive.approvals.start

Start an approval on a Google Drive file to request reviewer sign-off before content changes, optionally locking the file and setting a due date.

Instructions

Starts an approval on a file. For more information, see Manage approvals [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 StartApprovalRequest object accepting dueTime, fileContentChangeBehavior, lockFile, message, reviewerEmails; pass it via params or whole via body_file Siblings over the same resource: approve, cancel, comment, decline, get, list, reassign.

Input Schema

Name	Required	Description
`query`	No	Extra KEY=VALUE query pairs for endpoints whose parameters Discovery does not describe.
`fileId`	Yes	[URL path segment] Required. The ID of the file that the approval is created on.
`params`	No	Parameter map merged into the request; typed parameters win.
`dry_run`	No	Return the request that would be sent, without sending it.
`body_file`	No	Read the request body from this file ('-' for stdin) instead of building one from the parameters. The body is a JSON StartApprovalRequest object.
`request_body`	No	Request body of type StartApprovalRequest: pass it via `params` (merged into the built body) or whole via `body_file`.

Output Schema

Name	Required	Description	Default
`kind`	No
`status`	No
`dueTime`	No
`initiator`	No
`approvalId`	No
`createTime`	No
`modifyTime`	No
`completeTime`	No
`targetFileId`	No
`reviewerResponses`	No
`fileContentChangeBehavior`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 26, 2026

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 StartApprovalRequest object."

addedInput schema / properties / request_body

Added value: +{
+  "description": "Request body of type StartApprovalRequest: pass it via `params` (merged into the built body) or whole via `body_file`.",
+  "properties": {
+    "dueTime": {
+      "type": "string"
+    },
+    "fileContentChangeBehavior": {
+      "enum": [
+        "FILE_CONTENT_CHANGE_BEHAVIOR_UNSPECIFIED",
+        "RESET_APPROVAL",
+        "NO_APPROVAL_ACTION"
+      ],
+      "type": "string"
+    },
+    "lockFile": {
+      "type": "boolean"
+    },
+    "message": {
+      "type": "string"
+    },
+    "reviewerEmails": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Changed2 schema fields changedOct 26, 2026

changedInput schema / properties / fileId / description

Previous value: -"Required. The ID of the file that the approval is created on."New value: +"[URL path segment] Required. The ID of the file that the approval is created on."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "approvalId": {
+      "type": "string"
+    },
+    "completeTime": {
+      "type": "string"
+    },
+    "createTime": {
+      "type": "string"
+    },
+    "dueTime": {
+      "type": "string"
+    },
+    "fileContentChangeBehavior": {
+      "enum": [
+        "FILE_CONTENT_CHANGE_BEHAVIOR_UNSPECIFIED",
+        "RESET_APPROVAL",
+        "NO_APPROVAL_ACTION"
+      ],
+      "type": "string"
+    },
+    "initiator": {
+      "properties": {
+        "displayName": {
+          "type": "string"
+        },
+        "emailAddress": {
+          "type": "string"
+        },
+        "kind": {
+          "type": "string"
+        },
+        "me": {
+          "type": "boolean"
+        },
+        "permissionId": {
+          "type": "string"
+        },
+        "photoLink": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "kind": {
+      "type": "string"
+    },
+    "modifyTime": {
+      "type": "string"
+    },
+    "reviewerResponses": {
+      "items": {
+        "properties": {
+          "kind": {
+            "type": "string"
+          },
+          "response": {
+            "enum": [
+              "RESPONSE_UNSPECIFIED",
+              "NO_RESPONSE",
+              "APPROVED",
+              "DECLINED"
+            ],
+            "type": "string"
+          },
+          "reviewer": {
+            "properties": {
+              "displayName": {
+                "type": "string"
+              },
+              "emailAddress": {
+                "type": "string"
+              },
+              "kind": {
+                "type": "string"
+              },
+              "me": {
+                "type": "boolean"
+              },
+              "permissionId": {
+                "type": "string"
+              },
+              "photoLink": {
+                "type": "string"
+              }
+            },
+            "type": "object"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "status": {
+      "enum": [
+        "STATUS_UNSPECIFIED",
+        "IN_PROGRESS",
+        "APPROVED",
+        "CANCELLED",
+        "DECLINED"
+      ],
+      "type": "string"
+    },
+    "targetFileId": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedOct 26, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the load and does well: it declares the mutation nature ("creates or triggers a change"), the readonly safety-profile refusal, the HTTP method, and the return shape (API response as JSON). It doesn't cover auth requirements or side effects like notification of reviewers, keeping it below 5.

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

Conciseness3/5

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

Purpose is front-loaded in the first sentence, but the remainder is a dense run-on of docs link, HTTP method, safety note, return format, body fields, and sibling list crammed with em-dashes. Every element is relevant, but the packaging harms scannability.

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 mutating tool with nested-object params and no annotations, the description covers purpose, safety gating, body structure, and alternatives; an output schema exists so return-value detail is a bonus. It lacks permission/auth detail but is otherwise complete.

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 coverage is 100%, so the schema already documents all six parameters, giving baseline 3. The description restates the body fields (dueTime, fileContentChangeBehavior, lockFile, message, reviewerEmails) and the params/body_file routing, but adds little beyond what the schema already conveys.

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+resource ("Starts an approval on a file") and explicitly distinguishes itself from siblings on the same resource (approve, cancel, comment, decline, get, list, reassign). An agent can immediately tell this is the creation action versus the manage/list actions.

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 a when-not condition ("refused under --readonly safety profiles") and enumerates sibling alternatives over the same resource, providing clear context for choosing this tool. It stops short of stating explicit selection criteria between start vs. approve/etc., so not a full 5.

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

Deploy Server