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

Annotations already declare readOnly/idempotent/non-destructive, so that ground is covered. The description adds genuinely new context: chronological ordering and cursor-based incremental fetching. It doesn't mention pagination limits or ordering stability, but the added value above annotations is real.

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?

Two sentences, zero waste, with the resource/ordering front-loaded and the cursor-follow-up pattern as the second point.

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 4-param read feed with no output schema, the description covers ordering, event types, and the cursor return-value linkage. The main omission is the undocumented `limit` bound, but overall an agent has what it 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 50%. The description usefully ties `after` to meta.next_cursor, and the schema documents `after`, `include_order`, and the `type` enum. However `limit` (bounds 1-200) is undocumented in both description and schema, so the description doesn't fully compensate.

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 resource (order events) and enumerates the event types (order.created, order.status_changed) plus chronological ordering. It's clearly distinct from single-order siblings like get_order, though it doesn't explicitly name them.

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?

Explains a polling pattern (pass meta.next_cursor as `after` to get only new events), which implies ongoing-feed usage, but gives no explicit when-to-use versus alternatives or when-not conditions.

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