> For the complete documentation index, see [llms.txt](https://docs.storylane.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.storylane.io/mcp/storylane-mcp/limits-and-processing-time.md).

# Limits & Processing Time

How long async jobs take, how pagination works, and how to keep token usage down.

## Limits and processing times

#### Asynchronous tools

Some tools return immediately with a job ID rather than a finished result. Poll `get_demo_status` until processing completes.

| Tool                     | Typical time     |
| ------------------------ | ---------------- |
| `convert_url_to_demo`    | 10 to 20 minutes |
| `convert_video_to_demo`  | Under 10 minutes |
| `convert_images_to_demo` | Under 5 minutes  |
| `personalise_demo`       | Under 5 minutes  |
| `create_hub`             | Under 5 minutes  |

{% hint style="info" %}
A demo that is still processing has no shareable link. Publish only after status returns complete, and always poll rather than assuming a fixed wait.
{% endhint %}

#### Pagination

List tools are paginated. Defaults differ by tool, so ask for a page size or a limit when you want a specific number.

| Tool                 | Default page size |
| -------------------- | ----------------- |
| `list_demos`         | 100               |
| `repx_list_topics`   | 40                |
| `repx_get_analytics` | 25                |

#### Keeping token usage down

Token usage comes from two places: the tool definitions your client loads, and the data each tool returns.

* **Enable only the tools you need.** Every enabled tool adds to every request.
* **Be specific.** "Analytics for \[demo name], last 30 days" costs far less than "how are my demos doing", which makes the agent list and check everything.
* **Use the lightest tool.** `get_demo_status` instead of `get_demo` when you only need to know whether processing finished.
* **Narrow large queries.** Add date ranges, filters, or limits to `list_demos`, `list_leads`, `list_accounts`, `get_demo_analytics`, and `repx_get_analytics`.
* **Start a new chat per task.** Long conversations resend earlier tool results with every message.
* **Use a smaller model for routine work.** Pulling leads or creating links does not need your most capable model.

{% hint style="info" %}
`repx_get_analytics` is the heaviest tool available. Each page returns 25 full session records including conversation summaries and nested lead data. Always scope it.
{% endhint %}

#### Feature and plan requirements

| Needs                        | Tools affected                                            |
| ---------------------------- | --------------------------------------------------------- |
| Starter plan or above        | All MCP tools                                             |
| Connected CRM, Deals enabled | `list_crm_pipelines`, `list_crm_stages`, `list_crm_deals` |
| Alerts enabled, paid plan    | `list_alerts`, `create_alert`, `update_alert`             |
| Hubs enabled                 | `create_hub`                                              |
| Creator role or above        | `list_themes`                                             |
| OAuth client, not M2M        | `list_workspaces`, `switch_workspace`                     |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.storylane.io/mcp/storylane-mcp/limits-and-processing-time.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
