Tools reference Leave feedback

Tool	What it does
`get_annotations`	Lists every annotation in a document as JSON, with IDs, positions, and replies
`add_annotation`	Adds a highlight, comment, arrow, or other annotation and saves an annotated copy
`update_annotation`	Edits an existing annotation’s message or bounding box
`remove_annotations`	Removes annotations by ID, or clears all of them
`add_reply`	Adds a reply to an existing annotation — comment threads for review cycles
`remove_replies`	Removes replies by ID, by author, or all of them
`export_annotations`	Exports a document’s annotations to an XML file
`import_annotations`	Merges annotations from an XML file or another annotated document
`generate_pages_preview`	Renders pages as PNG images the AI client can display inline
`get_document_info`	Returns file type, page count, size, and per-page dimensions
`get_license_status`	Reports the active licensing mode and, under metered licensing, consumption

The FileInput shape

Every tool takes its document through the same file object — pass either a name from your storage folder or inline content:

{ "file": { "filePath": "contract.pdf" } }

Field	Type	Description
`filePath`	string	File path or name in the configured storage folder
`fileContent`	string	Base64-encoded file content (alternative to `filePath`)
`fileName`	string	Original filename with extension — required with `fileContent`. Since 26.9.0 it also works on its own, resolved from the storage folder exactly like `filePath`

You rarely write this JSON yourself: the AI agent does, from your plain-language prompt. Missing files are not an error to fear — the tool responds with the list of available files so the agent can correct itself.

We value your opinion. Your feedback will help us improve our documentation.

Tools reference Leave feedback

On this page

The FileInput shape

Was this page helpful?

Any additional feedback you'd like to share with us?

Please tell us how we can improve this page.

Thank you for your feedback!

On this page