mail_delete_mailbox

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

The description goes beyond annotations by adding: '[IRREVERSIBLE]' explicitly, and a known limitation about unreliability with cloud accounts. The destructiveHint annotation is true, but the description adds concrete context about failures.

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 a single, dense sentence that front-loads the most critical information: irreversibility, permanence, and known limitations. Every word adds value.

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?

Given the tool's destructive nature, the description covers essential behavioral context (permanence, confirm requirement, failure modes). No output schema exists, but return values are not critical here. One could argue a brief note on typical return on success/failure would improve completeness, but it's already strong.

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 low (33%), but the description compensates by specifying that confirm must be true (critical for destructive action). It does not elaborate on accountName or path, but the example '["INBOX"]' in schema provides some context. The added value of the confirm requirement is significant.

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 tool's purpose: 'Permanently delete a mailbox/folder and everything in it.' The wording is specific and leaves no ambiguity. It also distinguishes itself from related tools by emphasizing permanence and irreversibility.

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 includes a key usage requirement: 'Requires confirm:true.' It also alerts about potential failures with cloud-synced accounts. However, it does not explicitly mention alternatives or when to avoid using this tool, relying on the context of the warning instead.

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