Create a task

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

Adds substantial behavior beyond the annotations: Markdown descriptions are stored as HTML, subtasks remain in the parent's project unless a board/column is given, tags must already exist in Weeek, and — most valuably — the server verifies whether a task appeared after a failure and never creates a duplicate on its own, making retries safe. That duplicate-safety disclosure is exactly the kind of side-effect detail annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) cannot convey.

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

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

Front-loads the core create action and field list, then layers defaults, subtask behavior and retry safety in descending order of importance. It is dense but nearly every clause is actionable; only the 'Follow the conventions from weeek_context' line is a slightly vague placement.

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

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

For an 11-parameter mutation with no output schema, the description covers defaults, subtask routing, prerequisite tags and failure/retry semantics well. The main remaining gap is that it never hints at what a successful call returns (e.g. the new task id) or any permission requirements, which would be the last piece an agent needs.

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

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

Schema coverage is already 100%, so the baseline is 3, but the description adds meaning the schema lacks: `description` is Markdown converted to HTML, and `parent` implies subtask semantics with a board-placement rule plus a fallback to the parent's project. It also clarifies defaults for `board`/`column` and the existence requirement for `tags`.

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

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

States a specific verb+resource ('Creates a task on a board') and enumerates the resource's key fields (title, description, column, assignees, tags, priority, dates, files). This clearly distinguishes it from sibling mutations like weeek_update_task, weeek_move_task and weeek_attach_files.

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

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

Gives concrete selection guidance: board/column default to .weeek.json (defaultColumn), and `parent` is the switch for subtasks, with the notable caveat that a subtask only moves to a board when `board` or `column` is supplied. It also routes the agent to weeek_context for conventions and warns that tags must pre-exist, but it never explicitly states when to prefer weeek_attach_files or weeek_update_task over inline fields.

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