List Chats

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds ordering behavior (recency by default, relevance-by-name with `query`) and the returned field set, but says nothing about pagination/truncation beyond `limit`, or how `active_since` interacts with the recency ordering.

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?

Two tight sentences, front-loaded with the resource and return fields before the mode behavior. The returned-field enumeration partially duplicates the available output schema, but it is compact enough to aid tool selection.

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?

A read-only listing tool with annotations and an output schema does not need exhaustive disclosure, and the core selection behavior is present. Still, the undocumented `limit` parameter and the unstated meaning of `active_since` (last-message date vs. any activity) leave gaps an agent must guess at.

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 67%, so `query` and `active_since` are already documented in the schema, and the description only reinforces `query`'s approximate-name matching. `limit` has no description in the schema and is not mentioned in the description either, leaving page-size/pagination semantics to inference.

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?

Names a specific verb+resource ('Lista conversas do WhatsApp'), scopes it to groups and individuals, and enumerates the returned fields (id, nome, tipo, última mensagem, total). It implicitly separates itself from `search` by handling name matching with `query`, but never names a sibling explicitly.

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 useful behavioral guidance on the two modes: no `query` returns the most recent chats, with `query` returns closest name matches. It does not say when to prefer this over `search` (which could plausibly also find chats) or when to follow up with `get_messages`, so usage is implied rather than directed.

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