Batch Delete Messages

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is carried by structured data. The description's real added value is the human-confirmation requirement; 'Deletion is a mailbox mutation' largely restates what the annotations already say. It does not disclose the permanent-vs-Trash consequence or partial-failure behavior beyond what the schema states.

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 gating condition before the rationale. The second sentence adds little since the annotations already flag the mutation, but it costs only one line and reinforces intent.

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?

An output schema exists, so return values need not be explained, and the schema covers all four parameters. What is missing for a destructive batch tool is any note on atomicity/partial failures, recovery of trashed messages, or the 100-ID ceiling at the description level.

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 description coverage is 100%, so the schema already documents ids, permanent, mailbox_id, and if_in_state. The description only alludes to message IDs and adds no syntax, default, or interaction detail (e.g., how permanent interacts with recovery). Baseline 3 applies.

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 names a specific verb (delete) and resource (messages), and the prerequisite phrasing makes it unambiguously the destructive batch operation among the many mailbox_* siblings. It never says 'batch' or quantifies the scope, but the tool name plus the ID-list framing is enough to distinguish it from list/get/update siblings.

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 gives a clear gating condition: only when the user explicitly asks to delete and supplies or confirms IDs. That is strong when-to-use guidance for a destructive tool. It does not name an alternative path (e.g., when a softer action such as batch update or move-to-Trash is preferable), so it stops short of explicit when-not guidance.

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