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

Annotations already declare readOnly/idempotent/closed-world, so safety is covered; the description adds genuinely new behavior: result ordering (newest first), the fields each row carries (kind, event, actorName, readAt), and the null-means-unread convention. Cursor mechanics are described, though rate/limit behavior is left to the schema.

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?

Three dense sentences: scope first, then the row shape, then pagination. No filler, and the most decision-relevant information (what it reads and whose) is front-loaded.

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?

There is no output schema, so the description carries the return shape and it does so — row fields, ordering, and the cursor round-trip. Combined with the fully documented schema and read-only annotations, an agent has everything needed to call this once and then page correctly.

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 a baseline 3 applies, but the description adds meaning the schema lacks: 'pass nextBefore as before' links the page token in the response to the `before` parameter, and 'readAt (null = unread)' ties into unreadOnly. Only `limit` is left entirely to the 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?

States a specific verb and resource ('Read the caller's own notification inbox') and enumerates the content types it covers (assignments, mentions, comments on their tasks). 'Caller's own' plus 'notification inbox' clearly separates it from list_my_reminders, list_comments and the mark_*_read siblings.

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 clear context — the caller's own inbox only, newest first — and explains how to continue paging. It never names an alternative or an explicit when-not condition (e.g. use mark_all_notifications_read to clear, or unreadOnly instead of paging), so it stops short of full routing guidance.

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