Mark notifications read

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

Annotations already declare readOnlyHint=false, idempotentHint=true, openWorldHint=true, and destructiveHint=false. The description adds valuable context beyond annotations: all notifications up to now are affected, the unread count resets, and the action is invisible to other users. No contradiction exists.

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 short, information-dense sentences. The action and effect are front-loaded, followed by a concise privacy note. There is no redundant or filler wording.

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 mutation-style tool with two optional parameters and no output schema, the description plus schema covers what the tool does, its effect, its defaults, and its privacy implications. Nothing critical is missing for an agent to invoke it 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?

The input schema fully documents both parameters: account with default behavior and handle examples, and seen_at as an ISO timestamp defaulting to now. The description's 'up to now' reinforces the seen_at parameter but adds no new parameter-specific meaning beyond 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?

The description states the specific action: mark every notification up to now as seen, and the observable result: the unread count resets. It also clarifies the privacy scope, making it easy to distinguish from read-only notification tools like get_notifications and get_unread_count.

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 description clearly communicates when to use the tool: when the user wants to clear or reset the unread notification count. It provides context about scope ('affects only your own view') but does not explicitly name alternatives or state when not to use it.

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