Mark notifications read

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

Annotations already declare non-destructive, idempotent, and open-world, and the description adds genuinely new behavioral context: the effect is bulk ('every notification up to now'), it resets the unread count, and the visibility scope is private ('affects only your own view, and nobody else can tell'). That scope/privacy disclosure is exactly the kind of thing annotations cannot convey.

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 tight sentences with the effect front-loaded and the privacy caveat second; nothing is wasted and no filler.

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 mutation with no output schema and annotations covering safety, the description supplies what the structured fields cannot: the bulk scope and privacy semantics. It omits error behavior and how the account parameter resolves, but those are minor for a tool this simple.

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 both parameters (account, seen_at) are already fully documented. The description's 'up to now' loosely corroborates seen_at's default-to-now behavior but adds no syntax or format detail. Baseline 3 is appropriate.

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 every notification up to now as seen') plus the observable effect ('unread count resets'). It is clearly distinguished from read siblings like get_notifications by describing the mutation, though it does not name any sibling explicitly.

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 use case is implied by 'so the unread count resets', but there is no explicit when-to-use guidance, no prerequisites, and no mention of alternatives such as get_notifications or get_unread_count. Adequate but leaves routing to inference.

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