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

Annotations only declare readOnlyHint=false; the description adds the important behavioral facts that this is asynchronous, that it is not a live call, and that the audio must already be uploaded (no upload step, no recording). It does not say whether deletion/edit of the note is possible afterwards or whether encryption applies (note the sibling mDM_send_unencrypted), which would be useful for a mutation.

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, both front-loaded with the action and the mechanism; no filler and the usage cue comes after the definition in the right order.

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?

No output schema and only 5 params, so the description covers the important ground: async nature, message type, pre-uploaded asset. Missing is any indication of failure behavior or what `thread_label` does, which is the one parameter unexplained anywhere.

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 80%, so baseline is 3. The description reinforces the audio_url prerequisite ('already-uploaded audio clip'), which is already in the schema, and adds nothing about `to`, `mime`, `duration_ms`, or the otherwise-undocumented `thread_label`.

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 ('Send an asynchronous voice note to a contact') and pins down the mechanism: posts a `voice_note` message in the DM thread from a pre-uploaded clip. It does not, however, differentiate itself from the near-identical sibling mDM_send_voice, leaving the agent to guess which of the two to use.

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?

'Use for fire-and-forget voice instead of a live call' gives a clear when-to-use and implicitly names the alternative (mDM_call_start). The closest alternative, mDM_send_voice, is never mentioned, so the routing guidance is incomplete at the most ambiguous decision point.

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