Skip to main content
Glama
t-rhex

mcp-obsidian-vault

by t-rhex
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

create_task

Add a new task to the vault's task queue with YAML frontmatter for priority, dependencies, scope, context notes, and acceptance criteria. Automatically refreshes the task dashboard.

Instructions

Create a new task in the vault's task queue with structured YAML frontmatter. Tasks are markdown notes in the Tasks/ folder. Supports priority, type, dependencies, scope isolation, context notes, and acceptance criteria. Auto-refreshes the task dashboard.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dueNoOptional deadline in YYYY-MM-DD format.
tagsNoTags for categorization.
typeNoType of work. Helps agents decide if they can handle it.other
scopeNoAdvisory: file paths this task intends to modify. Not enforced — agents should respect this to avoid conflicts.
titleYesShort, descriptive title for the task.
sourceNoWhere this task came from (e.g. 'manual', 'github-issue-42', 'agent-spawned').manual
projectNoProject ID to attach this task to (e.g. 'proj-2026-03-09-abc123'). Task will appear in get_project_status rollups.
assigneeNoOptionally pre-assign to a specific agent.
priorityNoTask priority. Default: medium.medium
reviewerNoWho should review this task (optional).
depends_onNoTask IDs that must complete before this task can start.
risk_levelNoRisk level. High/critical tasks auto-require review on completion.
descriptionYesDetailed description of what needs to be done. Include context, constraints, and links to relevant notes.
escalate_toNoAgent ID or 'human' to escalate to after max_retries exhausted.
max_retriesNoMax auto-retries on failure. 0 = no auto-retry (default).
parent_taskNoID of the parent task, if this is a sub-task.
context_notesNoPaths to vault notes that provide context for this task (e.g. 'Projects/my-api').
routing_rulesNoConditional workflow rules. When this task completes, evaluate rules against output to selectively unblock/cancel dependents.
review_requiredNoIf true, complete_task sends to needs_review instead of completed. Human must approve.
timeout_minutesNoMax time in minutes before an agent is considered stuck. Default: 60.
acceptance_criteriaNoList of criteria that must be met for the task to be considered complete.
retry_delay_minutesNoMinutes to wait between retries. Default: 5.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral disclosure burden. It discloses that the tool creates a markdown note, stores it in Tasks/, uses YAML frontmatter, and auto-refreshes the task dashboard. These are meaningful side effects beyond the schema, though it could also mention what the tool returns.

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

Conciseness5/5

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

Three terse sentences: primary action, storage location, and key behavioral side effect. No filler or redundant restatement of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 22-parameter tool with no output schema, the description gives enough selection and invocation context: what it creates, where tasks live, what fields are supported, and the dashboard refresh side effect. It does not mention the returned task ID or how the agent should reference the created task, which is a minor gap given dependency-related parameters.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds value by grouping key parameters (priority, type, dependencies, scope isolation, context notes, acceptance criteria) and explaining that parameters become structured YAML frontmatter, which helps agents understand the data model beyond the 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?

Clearly states the verb ('Create') and resource ('new task in the vault's task queue') with the storage format ('structured YAML frontmatter'). It also distinguishes the tool from generic note creation by explaining that tasks are markdown notes in the Tasks/ folder.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: 'Create a new task' signals this is for new tasks, and sibling tools like update_task and complete_task cover other lifecycle stages. However, the description never explicitly states when not to use this tool or names an alternative for related operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools