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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety bar is met without the text. The description adds genuine behavioral value on top: it discloses that results are a merge across four heterogeneous sources and that ordering is by overdue-ness, which an agent cannot infer from the annotations. It omits pagination behavior and whether an empty result means "nothing to do" versus "no data," keeping 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?

Two sentences, both front-loaded with the highest-value information: the scope and the four constituent sources come first, the ordering rule second, and the sibling disambiguation last. There is no filler and no restatement of the title.

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 an output schema present, the description correctly does not spend words on return shape, and it does cover the scope, composition, and ordering that an agent needs to call it sensibly. The remaining gap is operational: default page size and how to continue via cursor are not mentioned anywhere the agent can see, since the schema documents none of it.

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 carries the full burden, and it only partly does. The four named sources map cleanly onto the enum values in the `sources` parameter, which is useful, but it never says that `sources` filters the merge, and it says nothing at all about `limit` (max 50) or `cursor` pagination — two of three parameters left entirely to the bare 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?

The description states a specific resource (a merged queue) and enumerates exactly what it aggregates: awaiting-reply conversations, due alarms, overdue tasks, and new business signals. It also gives the ordering rule ("most overdue first") and explicitly names the sibling list_conversations(awaiting_reply) as covering only a subset, so an agent can distinguish it without opening any 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?

It frames the use case crisply as "what should I follow up on" and disambiguates against the narrowest competing sibling. It stops short of naming when NOT to use it — e.g., that list_tasks or list_business_signals should be preferred when only one source (or a full, unfiltered listing) is wanted — so the exclusion guidance covers one sibling rather than the space.

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