Skip to main content
Glama

task_extract_from_image

Extract tasks from an image by supplying a file path or existing attachment. Preview proposed tasks with a dry run, then confirm to create them in a target OmniFocus project.

Instructions

Capture tasks from an image — agent does vision, tool does plumbing. Source is a path or existing OF attachment; agent supplies proposed: ProposedTask[]. Two-phase: dryRun=true validates+echoes; dryRun=false with confirmation[] writes. attachSourceTo: 'parent-task' (default), 'each-task' (path-mode only), or 'none'. Path-mode: PNG/JPEG/HEIC/HEIF/GIF/WEBP/PDF; respects attachment-path-scope + size cap. Do NOT use when you already have structured tasks — call task_batch_create. Returns { phase, proposed?, parent?, created?, outcome? }. Side effects: dryRun=false creates tasks; call sync_trigger for cross-device. Example: task_extract_from_image({ source: { kind: "path", path: "/tmp/whiteboard.png" }, proposed: [{ name: "Follow up with Alice" }], dryRun: true })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dryRunNotrue (default) = preview; false requires confirmation[].
sourceYesImage source. attachment requires exactly one owner.
proposedYesAgent-supplied extraction.
confirmationNoRequired when dryRun=false. (Possibly-edited) confirmed tasks.
attachSourceToNoRe-attachment mode after task creation.parent-task
parentTaskNameNoWrapper parent task name; default 'Captured from image'.
targetProjectIdYesProject that receives the captured tasks (and the wrapper, if `parent-task` mode).
Behavior4/5

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

No annotations provided, so description carries full burden. It discloses side effects: dryRun=false creates tasks, and suggests sync_trigger for cross-device. Mentions path-mode constraints and size cap. However, lacks details on error handling or rollback.

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?

Description is front-loaded with purpose, then covers usage, parameters, constraints, alternatives, side effects, and example. Every sentence adds value without redundancy.

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?

With 7 parameters, no output schema, and no annotations, description covers core behavior, parameter meanings, and side effects. Lists return fields but could elaborate on error conditions. Overall fairly complete.

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?

Schema coverage is 100%, but description adds significant context: explains two-phase workflow, default values, path-mode restrictions, and attachSourceTo modes. Provides example with parameter values.

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 'Capture tasks from an image' and distinguishes from sibling tool task_batch_create by noting not to use when structured tasks exist.

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 says when to use (have image) and when not (already structured tasks). Details the two-phase process with dryRun and confirmation.

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/torsday/omnifocus-mcp'

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