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

Annotations already flag a destructive, non-idempotent write, so the safety baseline is covered. The description adds genuinely non-obvious traits: `script` is restricted to admin accounts and billed per character, and delete requires confirmation. It does not address what delete removes downstream (e.g., in-flight campaigns) or what the call returns.

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?

Very compact and front-loaded by action, with zero filler sentences. The telegraphic parenthetical style ('create (name; the user records the audio by phone in the app)') is dense enough to risk a misread but nothing is redundant.

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?

Covers the three mutations, the confirmation requirement, the cost-bearing admin path, and has no output schema to explain. However, for a destructive multi-action tool it omits prerequisites such as how to obtain a valid `id` and what happens to existing drops on delete, which an agent needs before calling update or delete.

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 75%, and the description compensates where it matters: it binds `name`/`script` to create/update, explains that audio originates from a phone recording unless `script` is used, and calls out admin-only plus per-character billing for `script`. The `id` parameter's sourcing (where to get it) is the only real gap.

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 states the resource ('Voicemail drops') and enumerates the operations the tool performs (create/update/delete), plus a conditional variant (script). An agent can tell this is the CRUD surface for voicemail drops, though it never names the sibling list/drop tools to sharpen the boundary.

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?

Per-action context is implied: create when the user records audio by phone, update only for renaming, delete after confirmation, script only on admin accounts. There is no explicit guidance on when to prefer voicemail_drops_list (to obtain ids) or voicemail_drops_drop (to actually send), so routing between siblings is left to inference.

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