Read notifications

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

Annotations already disclose the safety profile: read-only, idempotent, non-destructive, open-world. The description adds useful context about the content domain and the actionable meaning of mention, but it does not describe pagination, ordering, or response structure. There is no contradiction with annotations.

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: the first defines scope, the second gives high-value selection guidance. Nothing is wasted, and the actionable filtering tip is front-loaded for practical use.

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 read-only list tool with a well-described schema and strong annotations, the description is sufficiently complete: it states what notifications are included and how to filter. It could mention admin notification types or response ordering, but the schema's enum and pagination fields compensate.

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 input schema already documents all six parameters at 100% coverage, so the baseline is 3. The description adds value by framing the types parameter as a way to isolate notifications needing answers and by explaining that 'mention' is the actionable case, which helps the agent choose parameter values intentionally.

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 enumerates the notification kinds returned—mentions, boosts, favourites, follows, poll results, and edits—making the resource clear without being a pure tautology. Combined with the title 'Read notifications,' an agent can tell this is a read/list operation, though it doesn't explicitly state a verb like 'list' or 'fetch.'

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?

The description gives practical usage guidance: filter by type to get only actionable notifications, and specifically treat 'mention' as the item a human must deal with. It does not explicitly compare against siblings like dismiss_notification, clear_notifications, or get_read_position, so the agent has to infer when this read tool is preferred.

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