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

Annotations already declare destructiveHint=true and idempotentHint=true, so safety class is covered. The description adds genuine context beyond them: irreversibility ('No undo'), a required human-confirmation step, and the side-effect boundary that the linked sent copy is untouched — the last of which is not derivable from any structured field.

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?

Three short sentences, front-loaded with the action and the confirmation gate, then the irreversibility, then the scope boundary. No filler; every clause carries a distinct fact.

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 no explanation. For a destructive single-parameter tool, the description covers the safety class, the human-confirmation requirement, irreversibility, and the blast radius — nothing an agent needs to call it 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?

One parameter with 0% schema description coverage, but the schema itself carries strong typing (uuid format plus a strict regex pattern). The phrase 'confirming the exact target' hints at needing a precise, unambiguous identifier but adds no format or sourcing guidance. Baseline 3 given the schema already constrains the value shape.

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+resource ('delete a saved draft') and immediately scopes it against the closest siblings: it is not delete_sent_message/delete_message, and it explicitly notes the linked sent copy is separate. An agent can route correctly without opening any schema.

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?

Gives a clear precondition — confirm the exact target with the human before invoking — which is exactly the guidance an agent needs for a destructive call. It implicitly excludes the sent-copy deletion path, but does not name an alternative tool for that case, so it stops short of explicit when/when-not routing.

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