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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered elsewhere. The description adds genuine value beyond that by disclosing sort order ("newest first") and the shape of each returned row, but says nothing about pagination, total counts, or what happens past the limit.

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 front-loaded sentence with zero filler; the ordering and field list are appended compactly in parentheses. Every clause 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?

With no output schema, the inline field list (id | read | title | message) does real work in telling the agent what comes back, and ordering is stated. The only gap is pagination/truncation behavior when more notifications exist than the limit allows.

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 description coverage is 100%, so limit (default 20, max 100) and unreadOnly are already documented in the schema. The description mentions neither parameter and adds no meaning beyond it, so the baseline 3 applies.

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 ("List your notifications") plus the sort order and the returned fields, so an agent knows exactly what it gets back. It does not explicitly contrast itself with siblings like get_unread_counts or mark_notifications_read, which keeps it short of a 5.

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?

Usage is only implied by the verb "List" – an agent can infer this is the read path for notifications, and the sibling set makes the alternatives guessable. There is no explicit when-to-use or when-not-to-use guidance, and no mention of when to prefer get_unread_counts instead.

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