docs_createCreate a new Google Doc with a title. Returns the document ID needed for editing operations.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Title for the new document |
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | Document body structure | |
| error | No | Error code if connection failed | |
| title | No | Title of the created document | |
| message | No | Error message if connection failed | |
| documentId | No | ID of the newly created document |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "description": "Response from creating a new Google Doc",
+ "properties": {
+ "body": {
+ "description": "Document body structure",
+ "type": "object"
+ },
+ "documentId": {
+ "description": "ID of the newly created document",
+ "type": "string"
+ },
+ "error": {
+ "description": "Error code if connection failed",
+ "type": "string"
+ },
+ "message": {
+ "description": "Error message if connection failed",
+ "type": "string"
+ },
+ "title": {
+ "description": "Title of the created document",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "title": "Project Proposal"
+ },
+ {
+ "title": "Meeting Notes - Q4 2024"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds the return value context (document ID), which is useful. However, it does not explain behavioral implications like whether creating a doc with an existing title succeeds or any side effects beyond creation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of two short, front-loaded sentences that efficiently convey purpose and key output. Every word adds value, and there is no redundancy or unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having only one parameter, the description completely covers what the tool does and what it returns. The output schema existence is signaled, and the return value (document ID) is mentioned, which is sufficient for a simple creation tool given the annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the input schema already describes 'title' as 'Title for the new document'. The description only mentions 'with a title', adding no new meaning beyond the schema. The examples in the schema provide context, so the description is sufficient but not compensatory.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create', resource 'a Google Doc', and the key result 'returns the document ID needed for editing operations'. This effectively distinguishes it from sibling tools like docs_append_text, docs_get, etc., which focus on editing or reading existing documents.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear purpose but offers no explicit guidance on when to use this tool versus alternatives (e.g., when to create a new doc vs. edit an existing one using sibling tools). Usage is implied by the action, but no exclusions or context are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools are nearly indistinguishable: ask_pipeworx and ask_pipeworx_beta are explicitly identical in behavior, while ask_pipeworx_grounded and deep_research heavily overlap with the same router. The dense Polymarket tool cluster and discovery tools (discover_tools vs suggest_questions) further blur boundaries, though many individual tools do have distinct niches.
Names are consistently lowercase snake_case, which helps, but the convention is mixed: some are verb_noun (docs_create, list_subscriptions), some are noun phrases (entity_profile, deep_research, bet_research), and one uses a suffix (ask_pipeworx_beta). It is readable but not a predictable pattern across the set.
37 tools is already above the 25+ threshold, but the bigger problem is that the server is named Google_docs and only 6 of the 37 tools relate to Google Docs. The remaining 31 tools form a broad data-research and prediction-market platform, making the set feel bloated and mislabeled for its apparent purpose.
For a Google Docs server, the surface is incomplete: you can create, read, insert, replace, and append text, but there is no delete, no list/search, no formatting control, and no permission handling. The extensive Pipeworx and Polymarket tools cover a different domain entirely, so they do not fill the gaps in the docs workflow.