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

Annotations only cover readOnlyHint and openWorldHint, but the description adds real behavioral context: a hard cap of 20 matches, case-insensitive partial matching, the caveat that some groups (community announcement groups) may be missing, and disambiguation behavior. It also enumerates the returned fields including the null semantics for phone_jid/lid_jid, which matters because there is no output schema.

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 purpose and usage rules are front-loaded and well ordered, but the parenthetical field enumeration is dense and the punctuation is garbled ('phone_display: ...)., plus is_group'), which interrupts scanning. The return-field detail earns its place given no output schema, yet the sentence structure could be tightened considerably.

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?

With no output schema, the description compensates by describing return fields, match limit, and the is_group distinction plus canonical_jid usage for downstream calls (send_message, read_chat_history). Combined with the fallback guidance, an agent has everything needed to call this 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% for the single 'query' param, so the baseline is safe, but the description goes beyond it by adding 'nickname' (not in the schema wording) and by specifying case-insensitive partial matching and phone-digit matching. That gives the agent concrete query-construction guidance rather than restating the schema.

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 ('looks up') plus two precise resources (people in the user's WhatsApp contacts, and groups the user is in), with the match method spelled out (name, nickname, phone digits, case-insensitive partial group name). An agent can distinguish this from search_messages or get_recent_chats without opening either schema.

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?

Gives explicit when-to-use conditions ('when a name is ambiguous or before messaging a person or group the user hasn't talked to recently'), a disambiguation rule ('ask the user which one they mean'), and a named fallback sibling ('if a group isn't found, try get_recent_chats'). Nothing is left to inference.

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