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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: results are definitions plus a short answer preview only, system definitions appear inline marked is_system, and previews are untrusted customer-derived data that must not be treated as instructions. That injection warning is valuable context beyond structured fields; only the lack of anything about result volume/ordering keeps it from a 5.

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 core action, then filter semantics, then the sibling pointer and the security caveat – a sensible information order with little waste. The middle sentence is dense (parenthetical field list, format examples) but each clause earns its place.

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?

Covers purpose, filtering, return granularity, system-definition handling, trust caveat, and the follow-up tool, with an output schema carrying return shape. An agent has enough to call this correctly; only ordering/pagination or result-size expectations are unaddressed.

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 0%, so the description carries the full burden, and it does: chat_id accepts a WhatsApp chat id like 123@s.whatsapp.net or a numeric conversation_id, and its absence means list everything workspace-wide. Without this an agent would not know the accepted id formats.

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 and resource ("List the digest DEFINITIONS of this workspace") and enumerates exactly what a definition contains (name, question text, member chats, staleness state, is_system). It explicitly contrasts scope with the sibling get_chat_summary, so an agent can differentiate 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 a concrete use case for the parameter ("what questions are defined on this group?") and names the alternative for the other need: read a full stored answer one definition at a time with get_chat_summary. When-to-use and when-to-use-something-else are both present.

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