preview_cleanup

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

Annotations already mark read-only and non-destructive; description confirms nothing is modified and adds detail about confirm_token requirement for large operations.

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 purpose, 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?

No output schema; description mentions counts and confirm_token but not structure. Parameters unexplained. Adequate for a preview tool but incomplete.

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 0% and description does not explain the two parameters (account, decision). Account is only implied by 'one account' but not linked to parameter.

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?

Description clearly states it is a dry run for execute_decisions, providing counts and a confirm_token. Distinguishes from sibling execute_decisions.

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 positioned as a dry run before execute_decisions, implying usage context. No exclusions or alternatives, but clear enough given sibling context.

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