grr

Overview Schema Source Related Servers Discussions Admin

gmail.users.settings.cse.keypairs.list

Lists client-side encryption key pairs for an authenticated Gmail user, with pagination for managing encryption identities.

Instructions

Lists client-side encryption key pairs for an authenticated user. For administrators managing identities and keypairs for users in their organization, requests require authorization with a service account that has domain-wide delegation authority to impersonate users with the https://www.googleapis.com/auth/gmail.settings.basic scope. For users managing their own identities and keypairs, requests require [hardware key encryption [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, disable, enable, get, obliterate.

Input Schema

Name	Required	Description	Default
`query`	No	Extra KEY=VALUE query pairs for endpoints whose parameters Discovery does not describe.
`params`	No	Parameter map merged into the request; typed parameters win.
`userId`	Yes	[URL path segment] The requester's primary email address. To indicate the authenticated user, you can use the special value `me`.	me
`dry_run`	No	Return the request that would be sent, without sending it.
`pageSize`	No	[query parameter] The number of key pairs to return. If not provided, the page size will default to 20 entries.	20
`body_file`	No	Read the request body from this file ('-' for stdin) instead of building one from the parameters.
`pageToken`	No	[query parameter] Pagination token indicating which page of key pairs to return. If the token is not supplied, then the API will return the first page of results.

Output Schema

Name	Required	Description	Default
`cseKeyPairs`	No
`nextPageToken`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 26, 2026

addedInput schema / properties / pageSize / default
```
Added value: +"20"
```

changedInput schema / properties / pageSize / description

Previous value: -"The number of key pairs to return. If not provided, the page size will default to 20 entries."New value: +"[query parameter] The number of key pairs to return. If not provided, the page size will default to 20 entries."

addedInput schema / properties / pageSize / format
```
Added value: +"int32"
```

changedInput schema / properties / pageToken / description

Previous value: -"Pagination token indicating which page of key pairs to return. If the token is not supplied, then the API will return the first page of results."New value: +"[query parameter] Pagination token indicating which page of key pairs to return. If the token is not supplied, then the API will return the first page of results."

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

changedInput schema / properties / userId / description

Previous value: -"The requester's primary email address. To indicate the authenticated user, you can use the special value `me`."New value: +"[URL path segment] The requester's primary email address. To indicate the authenticated user, you can use the special value `me`."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "cseKeyPairs": {
+      "items": {
+        "properties": {
+          "disableTime": {
+            "type": "string"
+          },
+          "enablementState": {
+            "enum": [
+              "stateUnspecified",
+              "enabled",
+              "disabled"
+            ],
+            "type": "string"
+          },
+          "keyPairId": {
+            "type": "string"
+          },
+          "pem": {
+            "type": "string"
+          },
+          "pkcs7": {
+            "type": "string"
+          },
+          "privateKeyMetadata": {
+            "items": {
+              "properties": {
+                "hardwareKeyMetadata": {
+                  "properties": {
+                    "description": {
+                      "type": "string"
+                    }
+                  },
+                  "type": "object"
+                },
+                "kaclsKeyMetadata": {
+                  "properties": {
+                    "kaclsData": {
+                      "type": "string"
+                    },
+                    "kaclsUri": {
+                      "type": "string"
+                    }
+                  },
+                  "type": "object"
+                },
+                "privateKeyMetadataId": {
+                  "type": "string"
+                }
+              },
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "subjectEmailAddresses": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "nextPageToken": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedOct 26, 2026

TDQS

A3.6/5.0

Behavior4/5

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

With no annotations, the description carries the burden and discloses useful behavior: authorization requirements, HTTP GET, JSON response, and how request bodies relate to typed parameters or body_file. The user-managed auth clause is garbled/truncated, so the disclosure is not fully complete, but the read-only nature is clear from 'Lists' and 'HTTP 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 purpose is front-loaded and the sibling list is useful. However, the middle authorization sentence is malformed and includes generic request-body details that are awkward for a GET list operation, reducing clarity and conciseness.

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?

An output schema exists, so return values need not be explained. The description covers purpose, auth context, HTTP method, and response format, but the garbled non-admin authorization clause leaves a completeness gap for one important usage path.

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 the schema already explains userId, pageSize, and pageToken. The description adds generic context about typed parameters winning over the params map and body_file behavior, but it does not add list-specific parameter guidance beyond the schema.

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 states a specific verb and resource: 'Lists client-side encryption key pairs for an authenticated user.' It also names the sibling operations on the same resource, making the operation distinguishable from create/disable/enable/get/obliterate, though it does not explicitly contrast list with get.

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 provides authorization context for administrators versus users managing their own keypairs, which helps frame usage. However, it does not explicitly say when to choose this list operation over get or the other sibling operations, so usage guidance is mostly implied.

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

Deploy Server