get_document

Read one Montra document with its folder, tickets, and latest generation status.

Reads one document in full: the document itself, the folder it lives in, the status of its latest generation, and the tickets a reader sees in the app. Each ticket’s body is the markdown implementation spec — that is the work you are being asked to do.

Get a documentId from list_documents. For the typical read-then-implement loop, see the agent workflow guide.

Input

documentId · string (uuid) · required

Id of the document to read, as returned by list_documents.

Output

document · object · required

Show properties

id · string · required

Document id.

title · string · required

Document title.

summary · string · required

Short summary of the document. Empty when none has been written.

status · string · required

Document status.

completed · boolean · required

Whether the document has been marked complete.

folderId · string · required

Id of the folder holding this document. null when the document is not in a folder.

createdAt · string · required

When the document was created.

updatedAt · string · required

When the document was last updated.

folder · object

The folder holding the document. null when the document is not in a folder.

Show properties

id · string · required

Folder id.

name · string · required

Folder name.

description · string · required

Folder description. Empty when none has been written.

generation · object

Status of the document’s latest generation. null when nothing has been generated yet.

Show properties

status · string · required

Status of the latest generation.

updatedAt · string · required

When that generation last changed status.

tickets · object[] · required

Show properties

id · string · required

Ticket id. Pass this to get_ticket or get_ticket_images.

title · string · required

Ticket title.

summary · string · required

One-line summary of the ticket.

body · string · required

Markdown implementation spec. May be empty — see the notes below.

status · string · required

Either todo or done.

imageCount · integer · required

How many screenshots are attached. Read them with get_ticket_images.

inputId · string · required

Id of the recording or other input this ticket came from. null when the ticket is not tied to one. Pass it to get_transcript for the narration behind it.

sortRank · string · required

Sort key. Tickets are already returned in this order.

timestampMs · integer · required

Position in the recording, in milliseconds, that the ticket refers to.

Notes

• Tickets that are hidden, deleted, or merged into another ticket are left out, so the list matches what a person sees in the app. The rest are returned in the app’s own order.
• A ticket’s body can come back empty when the document is read in a compact form. When that happens, read the ticket with get_ticket to get the full spec rather than treating it as an empty ticket.
• A document outside the bound workspace reads as not found, even if your user account can otherwise reach it — for example a document shared with you from another workspace. Resolve those with a share link instead.
• imageCount above zero means the person marked up real UI screenshots while recording. Fetch them with get_ticket_images and read them as part of the spec.