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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true. The description adds value beyond them by spelling out that deletion is permanent and that the default path is a non-destructive preview returning folder and message count — the key behavioral nuance an agent needs before invoking a destructive tool.

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 the destructive outcome and immediately followed by the preview default. No filler, no repetition of the title or annotations.

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 documented, yet the description still notes the preview payload (folder and message count). Combined with the clear destructive semantics, nothing an agent needs to call this safely is missing.

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 0% and the bare field is just 'confirm' with default false. The description compensates by explaining exactly what confirm=true changes — without it you get a preview, with it messages are permanently deleted — which is more than the schema conveys.

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?

States a specific verb and resource: 'Permanently delete every message in the Trash folder.' No sibling (flag/list/move/read/search/send) does anything similar, so the agent can select this unambiguously.

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 tells the agent the two operating modes: call it and you get a preview, add confirm=true to actually delete. That is clear contextual guidance, though it never explicitly frames it as 'use the default first as a safety check' nor names any alternative (none exists among siblings).

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