Complete or Drop Task

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

Adds critical behavior beyond annotations: detailed explanation of recurring task handling (complete advances, drop cancels series). No contradiction with annotations; idempotentHint true aligns with action semantics.

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?

Well-structured with summary, args, note, returns, and examples. Every sentence is informative and non-redundant. No wasted words.

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?

Covers purpose, all parameters with usage guidance, behavioral nuances, return value, and examples. No output schema but return description is sufficient. Fully equips agent to invoke correctly.

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 100%, but description adds value: explains priority rule, requirement of at least one, default for action, and provides clear examples that illustrate parameter usage.

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?

Clearly states 'Mark a task as complete or dropped in OmniFocus' with specific verb and resource. Distinguishes from siblings like delete_task and batch_complete_task by focusing on single task completion/dropping.

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?

Explicitly recommends using taskId from list/search results or taskName for natural language. Provides priority rule when both provided and states required presence. Could improve by mentioning when to use batch alternatives, but context from sibling names helps.

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