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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint as safe. The description adds useful behavioral context: the unread default, empty-for-new-accounts behavior, the non-backfill relationship to check_tracked_products, and that message is a short plain-text summary. 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?

Four short sentences deliver all key information with no filler. The core action is front-loaded, and each subsequent sentence adds either parameter behavior, result expectations, or output format context.

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?

Given the simple tool shape, complete schema coverage, output schema presence, and safe annotations, the description provides everything an agent needs for a correct call: default filter, result emptiness, distinction from a sibling tool, message format, and auth requirement.

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 the schema already documents all three parameters. The description adds minor clarification about the unread default and the response's message field, but limit and offset semantics remain fully handled by the schema. 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 clear verb and resource: 'List recall notifications for this API key.' It also distinguishes itself from the sibling check_tracked_products by explicitly saying it is 'not a backfill' of that tool, so an agent can identify its unique purpose.

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 explains how to get all notifications versus unread only, and sets expectations for empty results on new accounts. It also names check_tracked_products as a related but different operation. It does not enumerate every alternative sibling tool, but the guidance is sufficient for the common decision.

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