Create a new document. Use this when asked to create, write, draft, or compose a document, doc, note, page, article, or word document. Content should be HTML (e.g. "Hello").
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Document title | |
| content | No | HTML content of the document | |
| server_id | No | Server ID to create in (omit for personal) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. The only behavioral detail added is that content should be HTML, which is already stated in the input schema ('HTML content of the document'). The description does not mention side effects, permissions, return values, or success behavior, which is insufficient for a mutation tool.
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 three short sentences: a clear action statement, explicit usage triggers, and a format constraint with an example. Every sentence earns its place, and the most important information is front-loaded.
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?
The description is adequate for a simple 3-parameter tool with fully specified schema, but it lacks any mention of output/return behavior, prerequisites, or side effects. Given that this is a create operation with no output schema and no annotations, more context would be expected for full completeness.
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%, so the baseline is 3. The description adds only an example of HTML content ('<p>Hello</p>'), which is a minor reinforcement of the schema's 'HTML content' description. It does not materially enhance understanding of the other parameters (title, server_id).
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 tool's action ('Create a new document') and lists synonyms for when to use it ('create, write, draft, or compose a document, doc, note, page, article, or word document'). This distinguishes it from sibling tools like `create_sheet` or `create_slide_presentation` by specifying the resource type.
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?
Explicit usage guidance is provided: 'Use this when asked to create, write, draft, or compose a document...' This gives clear context for when to invoke the tool. However, it does not name explicit alternatives or exclusions, so it falls short of a perfect score.
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.
Every tool targets a distinct resource and action: document, sheet, tab, or presentation. Even similar operations like append_rows, append_slides, and append_to_document are clearly differentiated by their intended target.
The naming follows a predictable verb_noun pattern with create_, get_, list_, update_, delete_, and append_. Minor deviations like append_to_document (uses 'to') and the use of 'slide_presentation' vs 'slides' keep it from being perfectly uniform.
At 23 tools, the count is slightly above the ideal range, but each tool serves a clear purpose across three resource types (documents, sheets, slides). The volume is justified by supporting tab-level operations and append functionality.
The server provides full CRUD plus listing for each resource type, along with tab management and append operations. Minor gaps exist, such as lack of a direct 'set cell value' operation and no slide reorder or delete individual slide, but core workflows are well covered.