Unread message and notification counts

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds useful behavioral context beyond those annotations, including 'Cheap', 'in a single call', and 'across every course'. It is consistent with the annotations and gives a reasonable sense of scope and cost.

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 short sentences provide the output description, cost hint, and usage guidance with no wasted words. The core purpose is front-loaded and the guidance is immediately actionable.

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?

For a zero-parameter, read-only count tool the description is largely complete: it covers output scope, cost, and call context. The only minor gap is that the title mentions 'notification counts' while the description emphasizes messages, but this does not prevent an agent from correctly selecting and invoking the tool.

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?

The tool has zero parameters and the schema is empty, so there is nothing the description needs to explain about inputs. The baseline of 4 applies because parameter semantics are fully moot.

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 exactly what the tool returns: unread message counts across every course plus an overall messages summary. It clearly distinguishes itself from bb_list_conversations by focusing on aggregate counts rather than message contents.

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?

'Use it to decide whether reading messages is worth it before calling bb_list_conversations' explicitly states when to use this tool and names the relevant sibling alternative. The 'Cheap' qualifier also gives a clear cost-based reason to prefer it.

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