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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add operational detail — which it does: newest-activity sort, default open status, cursor-based pagination, and the read_circles scope requirement for circle_id. It doesn't state whether limit has a default value or what happens when next_cursor is exhausted.

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 verb, resource and sort order, then filters in a scannable run. It is dense and long, but nearly every clause is load-bearing (filter semantics, id sources, scopes); only the parenthetical UI-equivalence note borders on extra.

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?

Eight optional parameters, no output-schema gap to fill, and every filter with non-obvious semantics is explained. An agent could call this correctly — including paginating and resolving stage/circle ids — from the description alone.

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?

With 0% schema description coverage, the description carries the full burden and largely meets it: awaiting_reply is defined precisely (customer sent last message >1h ago with no answer, matching the inbox UI), labels is clarified as OR-semantics ("at least one"), and stage_id/circle_id reference the tools that supply their ids. limit and cursor are only partially covered — pagination is mentioned but the name in the schema is "cursor" and no default limit is given.

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 WhatsApp conversations") plus the default ordering ("newest activity first"). This clearly separates it from get_conversation (single item), list_bot_conversations (bot-only), and get_follow_up_queue (wider attention view) without needing the 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?

Names an explicit alternative (get_follow_up_queue) and the condition that selects it, and documents the default status=open so the agent knows the unfiltered call already excludes archived chats. It stops short of the full when/when-not matrix — nothing says when to prefer search_messages_and_contacts or list_bot_conversations over this.

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