Weft

Create Task

create_task

Use this when the user says 'add a task', 'remind me to …', or otherwise asks to capture work. If columnId is omitted the task goes to the Backlog. Priority defaults to medium unless urgency is implied (use 'high' for words like urgent/asap, 'low' for nice-to-have).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`dueAt`	No
`title`	Yes
`project`	No	Project name (case-insensitive) or project ID
`assignee`	No	Executor: a member's name or email (case-insensitive), 'me' to assign to yourself (the calling agent), or 'none' to unassign
`columnId`	No
`priority`	No		medium
`sprintId`	No
`blockedBy`	No	Tasks that must finish before this one can start. The task derives agentState "blocked" while any of them is open, leaves ready-sets, and unblocks itself the moment the last blocker completes. Cycles are refused.
`description`	No
`verification`	No	How to verify this task is actually done — the server executes these checks on complete_task. {mode, checks[]}: mode "executable"/"state_delta" lets fully-passed work move to Done by itself; "checklist"/"human" always stops at the user. Check kinds: http (GET url → expected status, optional mustContain phrase), citation (url + quote that must appear on the page), string_check (receipt must contain/equal/match value), file_hash (an artifact must carry this sha256), human_checklist (items only a person can judge — resolved when they accept). Give every task at least one machine check when you can: unverifiable "done" is the failure mode this board exists to close.
`requiresReview`	No	Stop at the user before this is called done. Set it ONLY for the irreversible: money, publishing outward, production, anything legal. Everything else finishes without them — a queue everything enters is a queue nobody reads.
`estimateMinutes`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already indicate this is a write operation (readOnlyHint false) and non-destructive. The description adds value by revealing default column and priority behaviors, but it doesn't disclose other behavioral traits such as duplicate handling, resulting task state, or confirmation output. That's acceptable given the annotation baseline, but not exceptional.

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 tight sentences, front-loaded with trigger phrases, followed by two high-value default rules. No filler or repetition of schema content.

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?

Given the large 12-parameter schema with complex nested objects, the description can't carry everything, but it covers the most decision-relevant defaults and usage context. Schema descriptions handle the remaining parameter meanings well enough for an agent to invoke this correctly.

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?

The description meaningfully fills gaps left by the schema: columnId has no default in the schema, yet the description states it defaults to Backlog, and priority gets nuanced guidance ('high' for urgent/asap, 'low' for nice-to-have). Other parameters rely on their schema descriptions, making this a good complement rather than full coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states this tool captures work via trigger phrases like 'add a task' and 'remind me to …', and the title confirms the create-task action. It doesn't explicitly distinguish itself from sibling bulk_create_tasks, but the singular 'a task' vs bulk is implied.

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

Usage Guidelines4/5

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

It provides explicit when-to-use trigger phrases and useful default behaviors (Backlog placement, medium priority). It doesn't mention when to prefer alternatives like bulk_create_tasks or add_task_to_sprint, but the guidance is actionable and clear.

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

All Weft tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?