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

Annotations already declare non-read-only, idempotent, non-destructive, so the bar is lower, yet the description adds real context: it needs a key, mutation is scoped to the caller's own inbox, and it returns the new unread count. It doesn't say whether previously-read items are skipped or how conflicts between modes resolve, keeping it short of a 5.

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?

One sentence, front-loaded with the action, then the mode choices, then the auth/scope/return facts. No filler and nothing ambiguous.

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 description supplies the return value (new unread count), plus auth and scope constraints and the three invocation modes. Nothing an agent needs to call this correctly is missing.

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 the baseline is 3, but the description goes further by framing the three parameters as alternative addressing modes in a single line, which the schema alone (independent descriptions) does not convey. It still doesn't state precedence if more than one mode is supplied.

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 ('Mark your notifications as read') plus scope ('only your own inbox'), which separates it from the sibling 'notifications' listing tool without requiring a schema 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?

It presents the three mutually exclusive modes (all, up_to, ids) which implicitly guides selection, and notes the auth requirement, but it never states when to prefer this over the sibling 'notifications' tool or what happens if several modes are combined.

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