Skip to main content
Glama
ampcome-mcps

Shortcut MCP Server

by ampcome-mcps

create-document

Create documents in Shortcut project management with HTML-formatted content and titles to organize project information.

Instructions

Create a new document in Shortcut with a title and content. Returns the document's id, title, and app_url. Note: Use HTML markup for the content (e.g., , , , ) rather than Markdown.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesThe title for the new document (max 256 characters)
contentYesThe content for the new document in HTML format (e.g., <p>Hello</p>, <h1>Title</h1>, <ul><li>Item</li></ul>)

Implementation Reference

  • Implements the core logic of the 'create-document' tool: calls client.createDoc with title and content, returns formatted success result with id, title, app_url or error message using toResult helper.
    private async createDocument(title: string, content: string) {
    	try {
    		const doc = await this.client.createDoc({
    			title,
    			content,
    		});
    
    		return this.toResult("Document created successfully", {
    			id: doc.id,
    			title: doc.title,
    			app_url: doc.app_url,
    		});
    	} catch (error) {
    		const errorMessage = error instanceof Error ? error.message : "Unknown error";
    		return this.toResult(`Failed to create document: ${errorMessage}`);
    	}
    }
  • Zod input schema defining 'title' (string, max 256 chars) and 'content' (string in HTML format).
    {
    	title: z.string().max(256).describe("The title for the new document (max 256 characters)"),
    	content: z
    		.string()
    		.describe(
    			"The content for the new document in HTML format (e.g., <p>Hello</p>, <h1>Title</h1>, <ul><li>Item</li></ul>)",
    		),
    },
  • Registers the 'create-document' tool on the MCP server, specifying name, description, input schema, and thin handler delegating to createDocument method.
    server.tool(
    	"create-document",
    	"Create a new document in Shortcut with a title and content. Returns the document's id, title, and app_url. Note: Use HTML markup for the content (e.g., <p>, <h1>, <ul>, <strong>) rather than Markdown.",
    	{
    		title: z.string().max(256).describe("The title for the new document (max 256 characters)"),
    		content: z
    			.string()
    			.describe(
    				"The content for the new document in HTML format (e.g., <p>Hello</p>, <h1>Title</h1>, <ul><li>Item</li></ul>)",
    			),
    	},
    	async ({ title, content }) => await tools.createDocument(title, content),
    );
  • BaseTools helper method to format MCP tool results as CallToolResult with a text content block containing message and optional pretty-printed JSON data.
    protected toResult(message: string, data?: unknown): CallToolResult {
    	return {
    		content: [
    			{
    				type: "text",
    				text: `${message}${data !== undefined ? `\n\n${JSON.stringify(data, null, 2)}` : ""}`,
    			},
    		],
    	};
    }
Behavior3/5

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

With no annotations provided, the description carries full burden. It discloses that the tool creates (a write operation) and returns specific fields (id, title, app_url), which is helpful. However, it doesn't mention permissions, rate limits, error conditions, or other behavioral traits like whether the document is immediately published or saved as draft.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficiently structured in two sentences: the first states the purpose and return values, the second provides a critical usage note about HTML markup. Every sentence adds value with zero waste, and key information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with no annotations and no output schema, the description provides basic purpose and return values, but lacks details on permissions, error handling, or system behavior. It's minimally adequate given the simple two-parameter schema, but could be more complete for a mutation operation.

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 both parameters thoroughly. The description adds marginal value by reinforcing that content uses HTML markup, but doesn't provide additional semantic context beyond what's in the schema. Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create a new document'), specifies the resource ('in Shortcut'), and lists the key inputs ('with a title and content'). It distinguishes from sibling tools like 'create-story' or 'create-epic' by focusing specifically on documents, not stories or epics.

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 description implies usage when creating documents in Shortcut, but provides no explicit guidance on when to use this tool versus alternatives like 'create-story' or 'create-epic'. It mentions HTML markup requirements, which offers some contextual usage hint, but lacks explicit when/when-not instructions or named alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ampcome-mcps/shortcut-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server