Poll the order event feed

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

Annotations already declare the operation as read-only, idempotent, open-world, and non-destructive. The description adds substantial behavioral context beyond those hints: it details the exact return shape, enumerates event types (state_change, new_order, receipt_issued), and clarifies that the feed is continuous and requires repeated polling with the returned cursor. This goes well beyond the annotations.

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 description is three sentences, front-loaded with the tool's purpose and HTTP endpoint, followed by the return shape and then usage guidance. Every sentence provides necessary information without fluff. It is compact yet rich enough to stand alone without an output schema.

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 one-parameter tool with no output schema, the description is remarkably complete. It explains the return structure, enumerates event types with their nested fields, and gives a clear pagination/polling loop. Together with the annotations and schema, an agent has everything needed to invoke and interpret results 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?

With 100% schema description coverage, the baseline is 3. The schema already explains that the cursor is opaque, should be omitted for the first page, and that exhaustion is indicated by a page with fewer items than limit. The description re-iterates the cursor usage and adds the 'continuous feed' nuance, but does not substantially add meaning beyond the schema's own parameter description.

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 clearly identifies a cursor-based order event feed with a specific verb ('Poll'), a resource ('order event feed'), and a scope ('new orders, state changes and issued receipts'). It distinguishes itself from sibling getters like get_order, get_orders_state, and get_receipt by framing the operation as a continuous feed rather than a direct lookup.

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 concrete usage instructions: omit cursor for the first call, keep passing the returned cursor, and poll again later with the last cursor. It implies continuous polling context, but it does not explicitly state when to prefer this tool over siblings such as get_orders_state or get_receipt, so it falls short of a full 5.

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