Create a new task in a project. Dates must be in YYYY-MM-DD format. End date is exclusive (a 1-day task has end = start + 1 day).
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| color | No | Hex color (e.g. #3b82f6) | |
| status | No | ||
| endDate | Yes | YYYY-MM-DD (exclusive end) | |
| parentId | No | Parent task ID for hierarchy | |
| progress | No | ||
| projectId | Yes | ||
| startDate | Yes | YYYY-MM-DD | |
| assigneeId | No | Profile ID of the assignee | |
| description | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses non-obvious behavior: date format (YYYY-MM-DD) and exclusive end date semantics (end = start + 1 for a 1-day task). This is valuable but does not cover other behavioral aspects like default values or return payload, so not a 5.
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?
Two sentences, front-loaded with the primary purpose, then the key date constraints. There is zero fluff and every sentence provides necessary operational detail.
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 a create operation with a rich schema and no output schema, the description covers the most error-prone aspect (date semantics) and clearly indicates the action. It omits details like defaults or required fields, but those are already visible in the schema, so the description is adequately complete for the tool's complexity.
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?
The schema already documents the date parameters, including the exclusive end note, so the description's date guidance partially duplicates schema info. The example clarifies the exclusivity but does not add meaning for the many other parameters (color, status, parentId, progress, etc.), which are undocumented in the description. This offsets the moderate schema coverage.
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?
The description clearly states the verb ("Create") and resource ("a new task in a project"), which distinguishes it from sibling tools like create_milestone and create_project. It is specific and unambiguous.
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?
The description gives clear context for when to use (creating tasks within projects) and includes important date-handling rules. It does not explicitly mention alternatives, but the context is sufficient given the tool name and sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource-action pair, such as create_task vs update_task vs set_task_progress. Even the two task-modifying tools have clearly separated concerns: one updates arbitrary fields, the other specifically updates progress with auto-derived status.
All tool names follow the verb_noun snake_case pattern (create_, list_, delete_, get_, add_, set_, update_). The only compound verb, reschedule_and_propagate, still fits the pattern and reads predictably.
15 tools is within the well-scoped 3-15 range, and each tool covers a meaningful operation for a project management domain. No redundant or trivial tools are present.
Tasks have full CRUD plus progress and dependency management, but milestones lack update/delete operations, and dependencies only support addition (no removal). These are notable gaps that may require workarounds in some workflows.
