Skip to main content
Glama

Update Task

vault_update_task

Change a task's status, priority, or Kanban lane in one atomic write. Compose multiple updates to complete, prioritize, or move tasks in your Obsidian vault.

Instructions

Update a task's status, priority, or Kanban lane in a single atomic call. Multiple mutations compose — status + priority + lane move all apply in one write cycle.

Example: vault_update_task({ path: "TASKS.md", block_id: "my-task", status: "done" }) — complete a task; on a Kanban board, auto-moves to the done lane Example: vault_update_task({ path: "TASKS.md", line: 42, priority: "high" }) — set priority Example: vault_update_task({ path: "TASKS.md", block_id: "my-task", status: "in_progress", lane: "Active" }) — start working and move to Active Example: vault_update_task({ path: "TASKS.md", block_id: "my-task", lane: "Up Next" }) — lane move without status change Example: vault_update_task({ path: "TASKS.md", line: 15, priority: "none" }) — remove priority

When to use: Any task state change — completing, starting, re-prioritizing, or moving between Kanban lanes. Use vault_list_tasks first to get identification fields (path + block_id or line). For Kanban boards with multiple done lanes, check done_lanes from vault_list_tasks to know which to pass.

Parameters:

  • Exactly one of block_id or line is required to identify the task.

  • At least one of status, priority, or lane is required (the mutation).

  • status changes the checkbox and manages dates: "done" appends ✅ date, "cancelled" appends ❌ date, "todo"/"in_progress" removes completion dates. On a Kanban board, "done" without an explicit lane auto-detects the done lane (via Complete marker, falling back to "Done" heading).

  • lane is only valid on notes with kanban-plugin frontmatter (is_kanban_task in vault_list_tasks).

  • format overrides the auto-detected Tasks plugin write format ("emoji" or "dataview"). When omitted, reads the Tasks plugin config from .obsidian/; defaults to emoji if .obsidian/ is not synced to the server. Both formats are always recognized for reading — only the write format is configurable.

Errors:

  • "note not found" — path does not exist

  • "no task at line N" — line doesn't contain a task checkbox

  • "block_id not found" — no task line ends with ^block_id

  • "at least one mutation required" — none of status, priority, or lane provided

  • "lane requires a Kanban board" — lane on a note without kanban-plugin frontmatter

  • "heading not found" — target lane doesn't exist; lists available headings

  • "multiple done lanes detected" — pass lane explicitly; check done_lanes from vault_list_tasks

  • "no done lane detected" — no Complete marker and no "Done" heading; pass lane explicitly

Returns: JSON { path, line, description, changes } — line is the final 1-based position (may shift after a lane move), description is a short excerpt, changes lists what was applied.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
laneNoTarget Kanban lane heading for a lane move. Only valid on Kanban boards.
lineNo1-based line number from vault_list_tasks. Fragile if the file changed since the query.
pathYesVault-relative path to the note containing the task (must end in ".md")
formatNoField format for new metadata (done dates, priority). Overrides the auto-detected Tasks plugin config. Default: auto-detected from .obsidian/ config, falling back to emoji.
statusNoTarget status. "done" appends ✅ date and auto-moves to done lane on Kanban boards. "cancelled" appends ❌ date.
block_idNoStable task identifier — the ^block-id at the end of the task line, without the ^. Preferred over line.
priorityNoTarget priority. "none" removes the priority emoji.
Behavior5/5

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

Discloses atomic write behavior, auto-move on Kanban, date appending by status, format detection logic, and error conditions. No contradiction with annotations (destructiveHint=false, etc.).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with examples, use cases, parameter details, errors, and return. Slightly verbose but every sentence adds value. Could trim redundancy in parameter descriptions.

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?

Comprehensive: covers purpose, usage, all parameters, errors, return format. No output schema, but description provides return JSON structure. Fully adequate for agent invocation.

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

Parameters5/5

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

All 7 parameters have schema descriptions (100% coverage), but the description adds crucial context: exactly one of block_id/line required, at least one mutation, status effects on dates, lane validity, format override. Rich beyond schema.

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 description clearly states the tool updates a task's status, priority, or Kanban lane, with multiple examples reinforcing the purpose. It distinguishes itself from sibling tools like vault_list_tasks.

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?

Explicitly states 'When to use: Any task state change' and advises using vault_list_tasks first for identification. Provides error conditions and prerequisites, guiding appropriate 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/aliasunder/vault-cortex'

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