groups

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

With no annotations, the description carries the full burden and does so well: it discloses that create defaults to announce=true/restrict=true, that leave only ends your membership while the group survives, that participant_count includes the creator, and that self-invites dedupe into the owner slot. It omits permission/auth requirements (e.g., that update/leave may require admin rights) and any error or rate-limit behavior, so it is rich but not complete.

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?

Front-loaded with the action list, then notes, then examples — a clean hierarchy that lets an agent stop reading once it has what it needs. The examples largely restate the action bullets, so a bit of the content is redundant rather than additive.

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 5-action, 9-parameter dispatch tool with a nested settings object and no annotations or output schema, the description covers action semantics, defaults, edge cases, and one return-shape detail (create returns participants[] inline). An agent has enough to select and invoke any action correctly, with only minor uncertainty about list/get response shape.

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 0%, so the description must compensate, and it defines most of the 9 parameters: group_id with a concrete format example, participants as phone numbers, include_participants as inline member list, settings.announce/restrict with their meaning, query as an optional name filter, and skip/limit as offset pagination. The bounds (limit max 200, minimums) and the exact skip/limit parameter names are not surfaced, leaving a small gap.

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 domain (WhatsApp groups) and enumerates all five actions (list/get/create/update/leave) with the verb+resource for each, so an agent knows exactly what capability set is behind this tool. It also distinguishes the resource from sibling tools like chats and contacts by scoping everything to groups.

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 'Available actions' list plus the natural-language examples ('show me my groups', 'leave group g@g.us') give clear when-to-use routing for each action, and the 'leave' note explicitly says WhatsApp has no destroy-group, which prevents the wrong choice. It never contrasts itself with sibling tools (e.g., when to use groups vs chats for member info), so it falls short of a 5.

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