Skip to main content
Glama
SlideSpeak
by SlideSpeak

get_task_status

Check the status of a presentation generation task by ID, and retrieve the request ID upon completion to obtain the download URL.

Instructions

Get the current task status and result by task ID.
When the task completes, the result will contain a request_id.
Use the request_id with the downloadPresentation tool to get the download URL.

Possible statuses:
- PENDING: Task is queued
- SENT: Task has been sent for processing
- PROCESSING: Task is being processed
- SUCCESS: Task completed — result contains presentation_id and request_id
- FAILED: Task failed — result contains error details

If status is PENDING, SENT, or PROCESSING, poll again in a few seconds.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
task_idYes

Implementation Reference

  • The get_task_status MCP tool handler function. It takes a task_id, calls the SlideSpeak API at /task_status/{task_id} to check the status, and returns a formatted response. Handles statuses: PENDING, SENT, PROCESSING, SUCCESS, and FAILED.
    @mcp.tool()
    async def get_task_status(task_id: str) -> str:
        """
        Get the current task status and result by task ID.
        When the task completes, the result will contain a request_id.
        Use the request_id with the downloadPresentation tool to get the download URL.
    
        Possible statuses:
        - PENDING: Task is queued
        - SENT: Task has been sent for processing
        - PROCESSING: Task is being processed
        - SUCCESS: Task completed — result contains presentation_id and request_id
        - FAILED: Task failed — result contains error details
    
        If status is PENDING, SENT, or PROCESSING, poll again in a few seconds.
        """
        if not API_KEY:
            return "API Key is missing. Cannot process any requests."
    
        status = await _make_api_request("GET", f"/task_status/{task_id}", timeout=POLLING_TIMEOUT)
        if not status:
            return f"Failed to fetch status for task {task_id}."
    
        task_status = status.get("task_status")
        task_result = status.get("task_result")
    
        if task_status == "SUCCESS":
            request_id = None
            if isinstance(task_result, dict):
                request_id = task_result.get("request_id")
    
            result_str = json.dumps(status)
            if request_id:
                result_str += (
                    f"\n\nThe presentation is ready! Use downloadPresentation with "
                    f"request_id '{request_id}' to get the download URL."
                )
            return result_str
    
        elif task_status == "FAILED":
            return f"Task {task_id} failed. Details: {json.dumps(status)}"
    
        elif task_status in ("PENDING", "SENT", "PROCESSING"):
            return (
                f"Task {task_id} is still {task_status.lower()}. "
                f"Please call getTaskStatus again in a few seconds."
            )
    
        return json.dumps(status)
  • slidespeak.py:336-336 (registration)
    The @mcp.tool() decorator on line 336 registers get_task_status as an MCP tool with the FastMCP server.
    @mcp.tool()
Behavior5/5

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

No annotations are provided, so the description carries the full burden. It explains the possible statuses, the result structure (request_id, presentation_id, error details), and implies it is a read-only polling operation. No contradictions or missing critical behaviors are apparent.

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 concise and well-structured. It opens with the main purpose, then adds usage guidance and a list of statuses. Every sentence adds value, and the list is formatted for easy parsing.

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

Completeness5/5

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

Given a single required parameter, no output schema, and the tool being part of a workflow with a sibling download tool, the description sufficiently covers how to use the tool and what to expect. The status explanations and next-step instructions make it complete for the agent's decision-making.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter, 'task_id', is described in the schema title but with 0% schema description coverage. The description states 'by task ID', which conveys the parameter's purpose. However, it does not explain where the task_id originates or expects additional context. Still, it is adequate for a single parameter.

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 tool name 'get_task_status' is clear, and the description states: 'Get the current task status and result by task ID.' It also lists possible statuses, which adds clarity. The tool is distinct from siblings like download_presentation or generate_powerpoint, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly provides guidance on when to poll and what to do with the result: 'If status is PENDING, SENT, or PROCESSING, poll again... When the task completes, the result will contain a request_id. Use the request_id with the downloadPresentation tool.' This gives clear instructions for proper usage.

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/SlideSpeak/slidespeak-mcp'

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