grr

Overview Schema Source Related Servers Discussions Admin

drive.replies.get

Retrieves a specific reply by file, comment, and reply ID from Google Drive, returning JSON for comment and reply management.

Instructions

Gets a reply by ID. For more information, see Manage comments and replies [HTTP GET]. Returns the requested resource as JSON — request bodies are built from the typed parameters (typed flags win over the params map), or read whole from body_file Siblings over the same resource: create, delete, list, update.

Input Schema

Name	Required	Description	Default
`query`	No	Extra KEY=VALUE query pairs for endpoints whose parameters Discovery does not describe.
`fileId`	Yes	[URL path segment] The ID of the file.
`params`	No	Parameter map merged into the request; typed parameters win.
`dry_run`	No	Return the request that would be sent, without sending it.
`replyId`	Yes	[URL path segment] The ID of the reply.
`body_file`	No	Read the request body from this file ('-' for stdin) instead of building one from the parameters.
`commentId`	Yes	[URL path segment] The ID of the comment.
`includeDeleted`	No	[query parameter] Whether to return deleted replies. Deleted replies don't include their original content.	false

Output Schema

Name	Required	Description	Default
`id`	No
`kind`	No
`action`	No
`author`	No
`content`	No
`deleted`	No
`createdTime`	No
`htmlContent`	No
`modifiedTime`	No
`assigneeEmailAddress`	No
`mentionedEmailAddresses`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 26, 2026

changedInput schema / properties / commentId / description

Previous value: -"The ID of the comment."New value: +"[URL path segment] The ID of the comment."

changedInput schema / properties / fileId / description

Previous value: -"The ID of the file."New value: +"[URL path segment] The ID of the file."

addedInput schema / properties / includeDeleted / default
```
Added value: +"false"
```

changedInput schema / properties / includeDeleted / description

Previous value: -"Whether to return deleted replies. Deleted replies don't include their original content."New value: +"[query parameter] Whether to return deleted replies. Deleted replies don't include their original content."

changedInput schema / properties / replyId / description

Previous value: -"The ID of the reply."New value: +"[URL path segment] The ID of the reply."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "action": {
+      "type": "string"
+    },
+    "assigneeEmailAddress": {
+      "type": "string"
+    },
+    "author": {
+      "properties": {
+        "displayName": {
+          "type": "string"
+        },
+        "emailAddress": {
+          "type": "string"
+        },
+        "kind": {
+          "type": "string"
+        },
+        "me": {
+          "type": "boolean"
+        },
+        "permissionId": {
+          "type": "string"
+        },
+        "photoLink": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "content": {
+      "type": "string"
+    },
+    "createdTime": {
+      "type": "string"
+    },
+    "deleted": {
+      "type": "boolean"
+    },
+    "htmlContent": {
+      "type": "string"
+    },
+    "id": {
+      "type": "string"
+    },
+    "kind": {
+      "type": "string"
+    },
+    "mentionedEmailAddresses": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "modifiedTime": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedOct 26, 2026

TDQS

B3.3/5.0

Behavior3/5

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

No annotations are supplied, so the description carries the full burden; it does disclose '[HTTP GET]' (implying a read-only, non-destructive call) and that the response is the requested resource as JSON. However, it omits any permission/authorization context and, more problematically, spends its behavioural content on request-body assembly ('body_file', typed params winning), which is irrelevant boilerplate for a GET.

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?

The first sentence is well front-loaded, but the second is a long boilerplate clause about building request bodies that does not apply to a GET, followed by a doc link and a sibling roll-call. Roughly half the text is padding for this operation.

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 an output schema present and 100% schema coverage, return values and parameters need not be explained, so the core is covered. Still, the description leaves the caller without auth/scope hints and includes misleading request-body guidance for a read call, so it is adequate rather than 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 description coverage is 100%, so every parameter (fileId, commentId, replyId, includeDeleted, params, query, body_file, dry_run) is already documented in the schema; the baseline of 3 applies. The description adds only the generic precedence rule 'typed flags win over the `params` map', which the schema already states, and nothing about includeDeleted semantics or ID sourcing.

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?

"Gets a reply by ID" gives a specific verb and resource, and the sentence naming the siblings (create, delete, list, update) on the same resource helps an agent place this tool among near-identical neighbours. It stops short of saying which API/parent resource the reply belongs to (a Drive comment), which is a small ambiguity given the generic word 'reply'.

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 description enumerates the sibling operations over the same resource, which implies 'use this instead of list when you know the ID', but it never states that condition explicitly or says when not to use it. Usage has to be inferred from the verb rather than from stated guidance.

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

Deploy Server