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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive/closed-world, so safety is covered. The description adds genuinely useful behavior beyond that: deterministic ordering (GM thread first, then recency), per-thread payload contents (participants, last line, unread count), and a data-isolation guarantee ('Nothing here reaches another table').

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 resource and ordering, then isolation, then return fields — a logical progression with no filler. The main sentence is long and comma-chained, and the 'Returns:' line partially restates what the earlier clause already implied.

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 correctly names the returned fields (`threads`, total `unread`) and shape of each entry, and covers ordering and scoping. It is nearly complete for a one-parameter list tool, missing only guidance on follow-up calls (reading or marking threads).

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?

Single parameter with 100% schema description coverage ('the campaign, by its slug or its id'), so the baseline of 3 applies. The description adds no further detail about how campaign scoping interacts with the 'this table' isolation claim, so it does not compensate beyond 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+resource (list conversations) and pins the scope precisely: conversations 'you are in at this table,' with the GM thread first and direct threads most-recent-first. An agent can distinguish it from read_conversation (single thread) and list_notifications without opening a 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?

Scope is implied clearly ('every conversation you are in at this table'), which tells the agent when this is the right call for an overview. However, it never says when NOT to use it — it doesn't route to read_conversation for a single thread, mark_conversation_read for clearing the unread count, or count_unread_notifications, all of which are close siblings.

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