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

Annotations only say readOnlyHint=false, but the description discloses far more: the two-phase commit behavior (preview without side effect, then confirm to send), the 'write operation' nature, the broadcast visibility to all chat members, and the material risk that the unofficial Wacli client may trigger account restrictions for ToS violations. This substantially exceeds what annotations convey and is consistent with them (write op matches readOnlyHint=false; non-destructive matches destructiveHint=false).

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?

Each sentence adds a distinct fact: audience scope, chat_id provenance, confirm workflow, option/multi constraints, read-result routing, and ToS risk. The description is dense but front-loaded with the core purpose. It is slightly long, and the trailing count caveat plus risk warning could arguably be trimmed, but none of the content is filler for a tool with this complexity.

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 write tool with a confirmation gate, external dependency, and companion read tool, the description covers prerequisites, the two-step send protocol, parameter constraints, sibling routing, and risk. An output schema exists, so return-value shape is already documented structurally. Nothing material that an agent needs to invoke this tool correctly is missing.

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 100%, so the schema already documents every parameter. The description mostly restates schema content ('Give 2–12 options; set multi>1 to allow picking several' mirrors the schema's option-count and multi semantics), adding only interpretive emphasis rather than new meaning. Baseline 3 is appropriate since the schema carries the load.

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?

'Sends a poll to a WhatsApp chat/group' states a specific verb, direct object, and recipient scope, and 'everyone in the chat sees it' clarifies the broadcast semantics that distinguish it from a 1:1 message send. It also names the sibling sourcing tools (whatsapp_list_chats / whatsapp_list_groups) for chat_id, making its role unambiguous among the many whatsapp_* siblings.

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 gives an explicit workflow: first call with confirm=false returns a preview, confirm=true actually sends. It states where chat_id MUST come from, and routes the agent to whatsapp_read_poll for reading results while flagging that its count is indicative. This is explicit when/how-to-use guidance with named alternatives, not merely implied context.

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