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

Annotations already declare destructiveHint=true and idempotentHint=false. The description adds a specific caution: 'Do not send the same voice note repeatedly after an uncertain timeout; read chat state first', which is valuable operational guidance beyond the structured hints and does not contradict them.

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?

The description is three sentences, front-loads the main purpose, and includes the key operational caveat without any filler. Every sentence earns its place.

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?

It covers the essential usage points: provider support, prerequisite of resolving chat_id, content format, and duplicate-avoidance. It could benefit from explicitly contrasting with message_send_native_media or other senders, but the description is sufficiently self-contained for an agent to call it correctly.

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 86% (6/7 params have descriptions). The description reiterates 'base64 content + exact MIME type/filename' but adds little beyond schema. It adds a note about resolving chat_id, which is already in the schema. The description does not compensate for the one undocumented parameter (duration_seconds is described in schema, so actually 100%? Wait, duration_seconds has a description, so coverage is actually 100%? The signal says 86% but all properties have descriptions? Let's re-check: text, chat_id, filename, account_id, content_type, content_base64, duration_seconds all have descriptions. So coverage is 100%? But signal says 86% maybe because text is optional? Anyway, schema covers all. So description adds marginal value, baseline 3 is appropriate.

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 a specific verb and resource: 'Send an audio attachment as a native/playable voice note', and immediately specifies provider support (WhatsApp/Telegram). This clearly distinguishes it from generic send tools like messaging_send_message or message_send_native_media.

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 gives explicit usage conditions: 'where the connected provider supports it', and prerequisites: 'Resolve chat_id first', 'Provide base64 content + exact MIME type/filename', and 'read chat state first'. It does not name alternative tools for when not to use it, but the provider-support caveat is clear enough.

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