clear_sandbox

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

Annotations already indicate destructive and idempotent behavior, and the description adds valuable context beyond those: it guarantees the operation only applies to intercepted test messages, never real mail. This is a crucial safety trait for a destructive tool, even if details like irreversibility or authentication are not mentioned.

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 short sentences, front-loaded with the core action, and every word adds value. The second sentence is a precise safety qualifier rather than filler.

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 parameterless, simple deletion tool, the description is complete. It states the action, the scope, and the safety boundary. Annotations already cover idempotency and destructiveness, and no output schema is needed for this operation.

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 tool takes zero parameters and the schema is empty, so there is no parameter-level meaning to add. The description's scope clarification fully covers the only semantic ambiguity (what gets deleted), earning the baseline 4 for a no-parameter tool.

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 action ('Delete every captured sandbox email') with a specific verb and resource. It also distinguishes itself from related tools by scoping to sandbox emails ('Affects only intercepted test messages, never real sent mail'), making it distinct from list_sandbox_sends or send_email.

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 clearly implies when to use this tool (when you want to clear all captured sandbox emails) and provides an explicit when-not boundary by stating it never affects real sent mail. It does not name alternative tools for other email operations, but the context is clear enough for tool selection.

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