Create a task

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, etc.), the description discloses key behavioral traits: due time-of-day is discarded and never returned, notes are plain text with a max, tasks start as needsAction, hierarchy supports one nesting level, and recurrence is unsupported. No contradiction with annotations is present.

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?

The description is dense but every sentence carries operational value. It fronts the core purpose and return fields, then covers date semantics, limits, ordering, state, and a limitation—all in about 80 words with no filler or repetition.

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 6-parameter tool with no output schema, the description is remarkably complete: it lists return fields, explains ordering and nesting, sets expectations about state (needsAction), and flags the recurrence limitation. An agent can select and invoke this tool correctly without needing additional context.

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?

Even though schema coverage is 100%, the description adds meaning beyond the JSON schema: it explains how 'due' time is stripped, that parent creates a subtask with 'one level of nesting reliably', that omitting both parent and previous lands the task at the top, and that previous is a sibling insert-after. These semantics are not in the schema.

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 uses a specific verb and resource ('Creates a task in a list') and explicitly enumerates the return payload ('id, title, position, webViewLink, ...'). It also distinguishes itself from siblings like create_tasklist and update_task by focusing on task creation and returning the created object.

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 provides explicit when-not guidance: 'Recurrence cannot be created or read through the API' and 'New tasks start as needsAction — use complete_task to complete.' This routes the agent to an alternative tool under a clear condition, which is exactly what this dimension rewards.

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