Mark my notifications as read

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

Annotations carry destructiveHint and idempotentHint, and the description adds substantial context beyond them: irreversibility ('cannot be marked unread again'), scope limitation ('only notifications this connection can read'), and a consent requirement. This meaningfully explains the nature of the destructive action rather than just flagging it.

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?

Three sentences with zero waste: the first states the action and modes, the second the scope, the third the irreversibility and consent warning. Critical information is front-loaded and every sentence 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 destructive, irreversible mutation tool with an output schema and 100% schema coverage, the description covers what the tool does, both invocation modes, the source of ids, scope limits, and the user-consent precondition. Nothing an agent needs to call it safely 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 both parameters are already documented. The description adds a useful link between the ids parameter and list_notifications output, and between the all parameter and the 'or all of them' mode, but it does not add format or behavioral details beyond what the schema provides. 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?

The description states a specific verb+resource ('Mark the signed-in user's notifications as read') and clearly distinguishes the two modes: a subset via ids from list_notifications, or all. This differentiates it from the read-only sibling list_notifications and makes the tool's scope unambiguous.

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 on when to use the tool and an explicit guardrail: 'only do this when the user asked; they approve it first.' It also points to list_notifications as the source of ids, implying the correct workflow. It stops short of naming alternative tools explicitly, but the usage condition is concrete.

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