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

The description focuses on input syntax, not behavior. It does not disclose likely side effects, delivery guarantees, error conditions, or authorization requirements. Annotations provide only generic false hints, so the description must carry the transparency burden but does not.

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 compact and well-structured with clear action blocks, making it easy to scan. The closing '[Flattened action: media]' is cryptic and adds marginal value, but overall the description earns its length.

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?

The description covers most input parameters and the important address-format nuance, but it omits the `account` parameter, offers no return/error expectations, and provides no post-send behavioral detail. Without annotation or output schema support, this leaves meaningful gaps for the agent.

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?

With schema coverage at 0%, the description adds critical meaning: explains the `to` format, enumerates `type` values, gives the media source alternatives (media_url | media_base64), and optional fields like caption/filename/mimetype/reply_to. It misses describing the `account` parameter entirely.

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 clearly states 'Send a WhatsApp message (text or media)', identifying the verb and resource. It differentiates text vs media action shapes but does not explicitly distinguish this from the sibling whatsapp_send_text tool, despite overlapping text-sending capability.

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 provides concrete usage guidance for address formats ('JID' vs plain phone) and for groups ('always use the <id>@g.us JID — get it from whatsapp_groups'). However, it gives no guidance on when to choose this tool over whatsapp_send_text or other alternatives.

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