grr

Overview Schema Source Related Servers Discussions Admin

forms.forms.responses.list

Retrieve a form's submitted responses with optional timestamp filtering and pagination. Use it to review or export submissions for a specific form ID.

Instructions

List a form's responses [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: get.

Input Schema

Name	Required	Description
`query`	No	Extra KEY=VALUE query pairs for endpoints whose parameters Discovery does not describe.
`filter`	No	[query parameter] Which form responses to return. Currently, the only supported filters are: * timestamp > N which means to get all form responses submitted after (but not at)
`formId`	Yes	[URL path segment] Required. ID of the Form whose responses to list.
`params`	No	Parameter map merged into the request; typed parameters win.
`dry_run`	No	Return the request that would be sent, without sending it.
`pageSize`	No	[query parameter] The maximum number of responses to return. The service may return fewer than this value. If unspecified or zero, at most 5000 responses are returned.
`body_file`	No	Read the request body from this file ('-' for stdin) instead of building one from the parameters.
`pageToken`	No	[query parameter] A page token returned by a previous list response. If this field is set, the form and the values of the filter must be the same as for the original request.

Output Schema

Name	Required	Description	Default
`responses`	No
`nextPageToken`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 26, 2026

changedInput schema / properties / filter / description

Previous value: -"Which form responses to return. Currently, the only supported filters are: * timestamp > *N* which means to get all form responses submitted after (but not at) "New value: +"[query parameter] Which form responses to return. Currently, the only supported filters are: * timestamp > *N* which means to get all form responses submitted after (but not at) "

changedInput schema / properties / formId / description

Previous value: -"Required. ID of the Form whose responses to list."New value: +"[URL path segment] Required. ID of the Form whose responses to list."

changedInput schema / properties / pageSize / description

Previous value: -"The maximum number of responses to return. The service may return fewer than this value. If unspecified or zero, at most 5000 responses are returned."New value: +"[query parameter] The maximum number of responses to return. The service may return fewer than this value. If unspecified or zero, at most 5000 responses are returned."

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

changedInput schema / properties / pageToken / description

Previous value: -"A page token returned by a previous list response. If this field is set, the form and the values of the filter must be the same as for the original request."New value: +"[query parameter] A page token returned by a previous list response. If this field is set, the form and the values of the filter must be the same as for the original request."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "nextPageToken": {
+      "type": "string"
+    },
+    "responses": {
+      "items": {
+        "properties": {
+          "answers": {
+            "type": "object"
+          },
+          "createTime": {
+            "type": "string"
+          },
+          "formId": {
+            "type": "string"
+          },
+          "lastSubmittedTime": {
+            "type": "string"
+          },
+          "respondentEmail": {
+            "type": "string"
+          },
+          "responseId": {
+            "type": "string"
+          },
+          "totalScore": {
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

First observedOct 26, 2026

TDQS

B3.4/5.0

Behavior3/5

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

No annotations are provided, so the description must carry the behavioral burden. It discloses that this is an HTTP GET and returns JSON, which signals a read operation, but it does not cover permissions, rate limits, pagination behavior, or other operational constraints beyond that basic inference.

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 in the first sentence, which is effective. The second sentence, however, includes generic request-body and `body_file` mechanics that are largely irrelevant to a GET list operation and add noise rather than clarity.

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?

The description states the operation, HTTP method, and response format, while the schema fully documents the eight parameters and an output schema exists. Given that structured support, it is largely complete for invocation, though the lack of annotations means some behavioral context remains thin.

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 documents the parameters including `filter`, `pageSize`, `pageToken`, and `formId`. The description adds general request-building context about typed parameters and `body_file`, but does not add meaningful semantics for the list-specific parameters beyond what the schema provides.

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 starts with a specific verb and resource: "List a form's responses [HTTP GET]". It also names the sibling "get" over the same resource, which helps distinguish this as the collection-listing operation rather than a single-response retrieval. The remaining boilerplate about request bodies slightly dilutes the otherwise clear purpose.

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 HTTP GET label and the phrase "List a form's responses" imply that this tool should be used when enumerating responses, and the description points to the sibling "get" over the same resource. However, it does not explicitly state when to use this tool versus `forms.forms.responses.get`, nor does it give exclusions or prerequisites.

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

Deploy Server