mark_notifications_read

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

Without annotations, the description carries the behavioral disclosure burden. It clearly states the core effect (marks notifications read) and the scope (all vs. single), but it does not mention authentication needs, idempotency, or what happens to already-read notifications. These are not covered by annotations, leaving some behavioral context implicit.

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?

The description is a single sentence with no filler. The main action is stated first, and the optional-parameter condition is appended concisely. Every part earns its place.

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 one-parameter mutation tool, the description is mostly sufficient for invocation, but because there are no annotations and no output schema, it leaves gaps: it does not describe the return value, and 'all notifications' is ambiguous about whether that means the current user's notifications or a global scope.

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 schema provides only a type for notification_id with no description, so the description must add meaning. It does this well by explaining that presence of notification_id scopes the operation to a single notification and absence scopes it to all. It doesn't define the ID's origin, but that's reasonably inferable.

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 uses a specific verb ('mark'), a clear resource ('notifications'), and a target state ('as read'), and it further distinguishes all-notifications mode from single-notification mode via notification_id. This makes the tool's purpose unambiguous and separates it from read/list tools like list_notifications and mark_chat_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?

The description gives clear context for when to use the tool and explains the conditional: omit notification_id to mark all, provide it to mark one. It does not explicitly state when not to use it or name alternatives, so it falls just short of full usage guidance.

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