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

The description reveals critical operational behavior—the difference between an action being logged as a 'touch' versus a simple internal note—which is not captured by the provided safety or persistence annotations.

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 definition is appropriately sized for a tool with complex behavioral rules. The core function is front-loaded, followed by detailed, logical segmentation of its outcomes.

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?

The tool's behavior hinges on the context of the input (touch vs. note). The definition provides exhaustive context, leaving no ambiguity for an agent attempting to decide if this tool is appropriate for a given scenario.

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?

While 75% schema coverage exists, the description is crucial in defining the meaning and importance of the `medium` and `direction` parameters, tying them directly to the concept of a 'real touch.' This adds necessary semantic depth beyond the types.

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 ("Close") and clearly identifies the resource ("open next action"). It successfully frames the tool's role as the finalization mechanism for a specific type of task.

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?

It provides explicit conditional usage advice: if the action has a direction and medium, it's a 'real touch' (requiring logging); if not, it is an internal note. This is the highest level of guidance possible for this tool.

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