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

Annotations already declare readOnlyHint/idempotentHint, so the safety profile is covered; the description adds real behavior beyond that — default ordering (newest first), that unreadCount is bundled into normal responses, and that unread_only collapses the response to only the count. It omits page size / result limits, which is the main remaining gap.

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 compact clauses, no filler, with the primary purpose and ordering front-loaded before the parameter guidance. Every sentence carries information.

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 two-optional-parameter read tool with annotations covering safety and no output schema, the description supplies ordering, count semantics, and pagination. Only pagination limits (page size, max rows per call) are unstated, which is a minor omission.

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 coverage is 100%, so baseline is 3, but the description earns above baseline by explaining where the `before` value comes from ('an ISO timestamp from the last row') — a cursor-sourcing detail absent from the schema — and reinforcing the shape-switching effect of unread_only.

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?

Uses a specific verb+resource ('List your notifications') and immediately enumerates the content types (build finished, deploy failed, invitations), ordering (newest first), and an included aggregate (unread count). This clearly separates it from the sibling mutation tools mark_notification_read and mark_notifications_read.

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?

Gives concrete invocation guidance for both parameters: pass `before` from the last row to page back, and use unread_only=true to get just the count. It does not, however, explicitly state when to prefer this over mark_notifications_read or any other sibling, so routing is implied rather than spelled out.

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