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

Annotations already carry destructiveHint=true and readOnlyHint=false, so destructiveness is disclosed structurally. The description adds one valuable behavioral boundary — only already-read notifications are affected, leaving unread ones intact. It does not clarify whether 'delete' is permanent versus a trash/archive state, which is relevant given archive_notifications exists as a sibling.

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?

A single eight-word sentence that opens with the verb and states the full scope. Every word earns its place; there is no filler or redundant 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?

For a zero-parameter destructive bulk operation with an output schema present, the description conveys the action, the affected scope, and the exclusivity of the filter. The only remaining gap is an explicit reversibility statement distinguishing delete from the archive sibling, which would make it fully bulletproof.

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 zero parameters, there is nothing for the schema to document, and the description's phrasing 'all notifications that have already been read' confirms this is an unfiltered bulk operation. The baseline 4 for a zero-parameter tool applies, as no parameter semantics need to be added.

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 pairs a specific verb ('Delete') with a precise resource and scope ('all notifications that have already been read'), which clearly distinguishes it from sibling tools like archive_notifications (archive rather than delete), mark_notifications_read (marks rather than deletes), and count_unread_notifications. No ambiguity remains about what this tool accomplishes.

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 implies its use case — permanently removing already-read notifications — but never explicitly contrasts it with the nearest alternative, archive_notifications, which preserves history. An agent will likely choose correctly for a cleanup goal, but the description offers no explicit when-to-use vs when-not-to guidance relative to the notification-related siblings.

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