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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description still adds real context beyond them: the deletion is irreversible ('Cannot be undone') and the blast radius excludes posted replies. Remaining gaps (auth requirements) are minor.

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 tight sentences front-loaded with the action, followed by scope limits, irreversibility, and a concrete call example. Nothing is redundant or padding.

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 single-parameter destructive delete with an output schema available, the description covers what an agent needs: what is deleted, what is never affected, irreversibility, and valid id sources. Return values need not be explained given the output schema.

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% and the single draft_id parameter is fully documented including UUID format. The description repeats the same sourcing hint and adds a usage example, but adds no semantic detail the schema lacks; 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?

Specific verb+resource ('Deletes one unsent reply draft'), with scope narrowed to unsent drafts only. It explicitly contrasts with the sibling post_reply path by stating replies already posted to a store are never touched, so an agent can distinguish it from post_reply and list_drafts without opening a 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?

It tells the agent where draft_ids come from (list_drafts, draft_reply, create_reply_draft) and restricts applicability to drafts, which is clear usage context. It stops short of an explicit 'use this when / use X instead when' rule, but the boundary is unambiguous.

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