Broadcast a message

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

With no annotations present, the description carries the full burden of behavioral disclosure — and it delivers. It reveals the dry-run default, the recipient cap of 50, pacing of a few seconds apart, the privacy property (recipients do not see each other), and the ban risk that justifies the confirm flow. This is far beyond what annotations alone would typically provide.

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 sentences, front-loaded with the core purpose and the critical dry-run/confirm protocol. The ban warning is slightly long but earns its place because it justifies the confirmation gate. Minor trade: the parenthetical '(what a WhatsApp Broadcast List does under the hood)' is helpful context, and the structure places the cap/pacing after the protocol, which is acceptable.

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 6-parameter tool with no output schema and no annotations, this description is quite complete: it specifies the main workflow, limits, pacing, and risk profile. It doesn't explicitly state what the dry-run return looks like or what 'resolved' means for recipients, but the schema covers the skip_unresolved parameter and the overall context is sufficient for an agent to sequence calls 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 coverage is 100%, so the schema already documents all six parameters. The description adds meaning by explaining the overall send flow (dry-run then confirm=true) and by tying the pacing parameters to the 'paced a few seconds apart' note. It doesn't enumerate each parameter, but at 100% schema coverage it doesn't need to; the dry-run/confirm context is the main added semantic value.

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 opens with a specific verb-resource pair — 'Send the same message to many chats, one individual message each' — and immediately distinguishes it from a group message by explaining that recipients do not see each other, which sets it apart from sibling tools like send_message and broadcast_status. This is a clear, specific purpose.

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?

The description is exemplary: it states when to call once (dry run), when to call again after user approval (confirm=true), and explicitly warns against using it for people who did not opt in. It also names the risk context (bans) that should drive an agent's decision to require confirmation. Unlike siblings such as send_message, this tool is clearly meant for multi-recipient broadcast to opted-in contacts.

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