# Tools reference

All tools are available once your client is connected. The AI selects the appropriate tool automatically based on your request.

## generate\_slide

Generates a single PowerPoint slide from a natural-language prompt.

* **Cost:** 1 credit
* **Typical duration:** 3–7 minutes
* **Parameters:** `instruction` (string), `template_id` (optional string)

## edit\_slide

Edits a previously generated single slide.

* **Cost:** Free
* **Parameters:** `session_id` (from prior `generate_slide`), `instruction` (string)

## generate\_deck

Generates a full multi-slide PowerPoint deck. Runs through three phases (storyline → render → export); the AI chains the calls automatically.

* **Cost:** 1 credit per slide (charged after outline)
* **Typical duration:** 5–15 minutes for a 10-slide deck (\~2 min storyline + \~30 s per slide + \~1 min export)
* **Parameters:** `instruction` (string), `template_id` (optional string)

## edit\_deck\_slide

Edits a specific slide within a generated deck.

* **Cost:** Free
* **Parameters:** `deck_id`, `slide_number` (1-based), `instruction` (string)

## check\_generation\_status

Continues polling a generation that returned `status: "processing"`. Called automatically by the AI — you do not need to invoke this yourself.

* **Cost:** Free

## show\_slide\_preview

Renders the inline preview and download link for a completed slide or deck. Called automatically by the AI after generation completes.

* **Cost:** Free

## list\_templates

Lists PowerPoint templates available to your organization. The default template is flagged with `is_default: true`.

* **Cost:** Free
* **Parameters (all optional):**
  * `template_id` — look up a single template by id.
  * `query` — filter by template name (case-insensitive substring match).


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.perceptis.ai/perceptis-mcp-server/tools.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.