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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds genuinely useful context beyond them: the empty-until-published behavior, the fact it is not a backfill, the shape of message, and the API-key requirement.

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?

Front-loads the purpose, then tacks on behavioral notes in short fragments. Every sentence carries information, though the choppy sentence structure (multiple one-clause statements) is slightly less polished than a flowing description.

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?

An output schema exists, so return values need not be explained. The description covers auth requirements, the empty-state edge case, and the unread default, leaving little an agent needs to call 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?

Schema coverage is 100%, so the schema already documents limit, offset, and unread. The description only restates the unread default, adding no syntax or format detail 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?

States a specific verb and resource ('List recall notifications for this API key') and explicitly distinguishes itself from the sibling check_tracked_products by noting it is 'not a backfill of check_tracked_products.' An agent can identify this as a paginated notification-list tool without opening the schema.

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?

Gives clear usage context: the unread default and how to override it ('pass false for all'), plus the lifecycle note that results are empty for new accounts. It does not explicitly contrast against mark_notification_read, but the read-vs-mutate separation is intuitive from the names.

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