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

Beyond the readOnly, idempotent, and non-destructive annotations, the description adds important operational context: the required permissions are products:read, orders:read, and supply:write, and replay does not create progress, earnings, notifications, or external effects. It also clarifies that current_version is the latest version, not a historical event snapshot, which prevents a likely misinterpretation of the event data.

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 core action is front-loaded and the description is compact, with no obvious filler sentences. The permission list and version semantics are dense but useful. Minor jargon such as current_version appears without definition, but the overall structure is efficient.

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?

The description covers permissions, replay side effects, and version semantics, which are valuable for a read-only feed. However, with no output schema and no parameter descriptions, it omits the event payload shape, cursor and limit behavior, defaults, pagination termination, and error conditions. It is adequate but has clear gaps for an agent that must call the feed 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 description coverage is 0%, so the description must explain after and limit, but it only refers vaguely to a 'bounded cursor feed.' It does not define cursor meaning, default or maximum limit behavior, ordering, or pagination direction, leaving both parameters effectively undocumented.

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 action and resource: it polls a bounded cursor feed of business events. It also clarifies that events reference existing records and that current_version is the latest version, which helps distinguish this feed from record-looking siblings. However, it never explicitly names a sibling such as list_business_orders or get_business_order, so sibling differentiation is only implied.

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 some usage context by naming required permissions and saying to read the current record to continue after receiving an event. It does not say when to use this tool versus the many list_business_* and get_business_* siblings, nor does it state when not to poll. The guidance is implied rather than explicit.

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