docs_getRetrieve a Google Doc by ID. Returns title, formatted body content, and document structure.
| Name | Required | Description | Default |
|---|---|---|---|
| document_id | Yes | Document ID (from the URL) |
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | Document body structure | |
| error | No | Error code if connection failed | |
| title | No | Document title | |
| message | No | Error message if connection failed | |
| documentId | No | The document ID |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "description": "Google Doc with title, body content, and document structure",
+ "properties": {
+ "body": {
+ "description": "Document body structure",
+ "type": "object"
+ },
+ "documentId": {
+ "description": "The document ID",
+ "type": "string"
+ },
+ "error": {
+ "description": "Error code if connection failed",
+ "type": "string"
+ },
+ "message": {
+ "description": "Error message if connection failed",
+ "type": "string"
+ },
+ "title": {
+ "description": "Document title",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "document_id": "1BxiMVs0XRA5nFMKUVfGo6Q6XcYBCy_N1LCcFrZkZecc"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value by explicitly stating the return fields (title, formatted body content, document structure), giving the agent a clear picture of the behavioral outcome.
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 is a single, well-structured sentence with no redundant words. It conveys purpose and output efficiently.
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?
For a simple tool with one required parameter and an existing output schema, the description is complete: it states the action, the input identifier, and the output content. No major gaps are present.
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?
The input schema already describes the document_id parameter well ('Document ID (from the URL)') with 100% coverage. The description adds no further parameter details beyond 'by ID', so it meets the baseline but does not enhance.
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 'Retrieve' and the resource 'Google Doc by ID', and specifies the return values (title, formatted body content, document structure). This distinguishes it from sibling tools like docs_get_text (text only) and docs_append_text (write operation).
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 implies usage for retrieving full doc content but does not provide explicit guidance on when to use this tool versus alternatives like docs_get_text, nor does it mention when not to use it. Siblings exist but no comparison is made.
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.