grr

Overview Schema Source Related Servers Discussions Admin

gmail.users.drafts.get

Retrieve a specified Gmail draft by ID as JSON, with format options to inspect content, headers, or raw message data.

Instructions

Gets the specified draft. For more information, see Create and send draft emails [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, send, update.

Input Schema

Name	Required	Description	Default
`id`	Yes	[URL path segment] The ID of the draft to retrieve.
`query`	No	Extra KEY=VALUE query pairs for endpoints whose parameters Discovery does not describe.
`format`	No	[query parameter] The format to return the draft in. Values: `minimal` = Returns only email message ID and labels; does not return the email headers, body, or payload.; `full` = Returns the full email message data with body content parsed in the `payload` field; the `raw` field is not used. Format cannot be used when accessing the api using the gmail.metadata scope.; `raw` = Returns the full email message data with body content in the `raw` field as a base64url encoded string; the `payload` field is not used. Format cannot be used when accessing the api using the gmail.metadata scope.; `metadata` = Returns only email message ID, labels, and email headers..	full
`params`	No	Parameter map merged into the request; typed parameters win.
`userId`	Yes	[URL path segment] The user's email address. The special value `me` can be used to indicate the authenticated user.	me
`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.

Output Schema

Name	Required	Description	Default
`id`	No
`message`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 26, 2026

addedInput schema / properties / format / default
```
Added value: +"full"
```

changedInput schema / properties / format / description

Previous value: -"The format to return the draft in."New value: +"[query parameter] The format to return the draft in. Values: `minimal` = Returns only email message ID and labels; does not return the email headers, body, or payload.; `full` = Returns the full email message data with body content parsed in the `payload` field; the `raw` field is not used. Format cannot be used when accessing the api using the gmail.metadata scope.; `raw` = Returns the full email message data with body content in the `raw` field as a base64url encoded string; the `payload` field is not used. Format cannot be used when accessing the api using the gmail.metadata scope.; `metadata` = Returns only email message ID, labels, and email headers.."

changedInput schema / properties / id / description

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

addedInput schema / properties / userId / default
```
Added value: +"me"
```

changedInput schema / properties / userId / description

Previous value: -"The user's email address. The special value `me` can be used to indicate the authenticated user."New value: +"[URL path segment] The user's email address. The special value `me` can be used to indicate the authenticated user."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "id": {
+      "type": "string"
+    },
+    "message": {
+      "properties": {
+        "classificationLabelValues": {
+          "items": {
+            "properties": {
+              "fields": {
+                "items": {
+                  "properties": {
+                    "fieldId": {
+                      "type": "string"
+                    },
+                    "selection": {
+                      "type": "string"
+                    }
+                  },
+                  "type": "object"
+                },
+                "type": "array"
+              },
+              "labelId": {
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "historyId": {
+          "type": "string"
+        },
+        "id": {
+          "type": "string"
+        },
+        "internalDate": {
+          "type": "string"
+        },
+        "labelIds": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "payload": {
+          "properties": {
+            "body": {
+              "properties": {
+                "attachmentId": {
+                  "type": "string"
+                },
+                "data": {
+                  "type": "string"
+                },
+                "size": {
+                  "type": "integer"
+                }
+              },
+              "type": "object"
+            },
+            "filename": {
+              "type": "string"
+            },
+            "headers": {
+              "items": {
+                "properties": {
+                  "name": {
+                    "type": "string"
+                  },
+                  "value": {
+                    "type": "string"
+                  }
+                },
+                "type": "object"
+              },
+              "type": "array"
+            },
+            "mimeType": {
+              "type": "string"
+            },
+            "partId": {
+              "type": "string"
+            },
+            "parts": {
+              "items": {
+                "properties": {
+                  "body": {
+                    "type": "object"
+                  },
+                  "filename": {
+                    "type": "string"
+                  },
+                  "headers": {
+                    "items": {
+                      "type": "object"
+                    },
+                    "type": "array"
+                  },
+                  "mimeType": {
+                    "type": "string"
+                  },
+                  "partId": {
+                    "type": "string"
+                  },
+                  "parts": {
+                    "items": {
+                      "type": "object"
+                    },
+                    "type": "array"
+                  }
+                },
+                "type": "object"
+              },
+              "type": "array"
+            }
+          },
+          "type": "object"
+        },
+        "raw": {
+          "type": "string"
+        },
+        "sizeEstimate": {
+          "type": "integer"
+        },
+        "snippet": {
+          "type": "string"
+        },
+        "threadId": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "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 provided, so the description carries the full burden. It does disclose the HTTP method (GET) and that the result is JSON, which establishes read-only semantics. However, the sentence about building request bodies from typed parameters or `body_file` is inapplicable boilerplate for a GET with no body, and there is no mention of OAuth scope constraints or error behavior.

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?

Front-loads the purpose correctly, but the body-construction clause is irrelevant noise for a GET endpoint and the trailing sibling list is a comma-dump. Two of the four sentences do not earn their place for this particular tool.

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?

An output schema exists, so return values need not be explained, and all seven parameters are covered by the schema. What's missing is context an agent would want before invoking: required Gmail OAuth scopes, whether the draft's `raw`/`payload` availability depends on `format`, and the relationship to messages.get.

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%: id, userId, format (with enum values explained), query, params, dry_run, and body_file are all documented in the schema. The description adds nothing beyond that, so the baseline 3 applies.

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?

States a specific verb+resource ("Gets the specified draft") and explicitly enumerates the sibling operations over the same resource (create, delete, list, send, update), which lets an agent place it as the single-item read. It stops short of explaining how it differs from gmail.users.messages.get, but for its own family the differentiation is clear.

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?

Usage is only implied by the verb — retrieve one draft by id. The sibling list hints at alternatives but never says when to use get vs list (e.g. "use list to find ids") or what prerequisites exist (the draft must exist, scope requirements).

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

Deploy Server