Address open or historical orders

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

Adds substantial context beyond the readOnly/openWorld annotations: upstream cap of 100 for openDetailed with a 'capped' flag, historical limited to newest ~2000 with countsByStatus and coveredRange semantics, and page-size defaults (100 open / 50 rows). This is exactly the operational behavior an agent needs and is not derivable from the schema.

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?

Information-dense with zero filler; the mode breakdown is front-loaded after a one-line purpose statement. Jargon ('oid', 'TIF', 'coveredRange') assumes domain familiarity, but nothing is wasted.

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?

With no output schema, the description carries the return burden well, disclosing count, countsByStatus, coveredRange, per-mode row shape, and ISO time twins. An agent has enough to call it correctly and interpret the response.

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 baseline would be 3; the description goes further by explaining kind defaults, per-kind paging defaults, and the coin-substring filter intent. It adds real meaning over the raw schema without fully restating every parameter.

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 the specific resource ('Open Orders' / 'Order History') and enumerates the three retrieval modes with the fields each returns (coin, side, price, size, oid for open; trigger/TP-SL/reduce-only for openDetailed). It clearly reads as an order-listing tool, distinct from sibling fill/position tools, though it never names a sibling explicitly.

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 effective selection guidance by labeling kind='open' as the default and describing the distinct scope of each mode, so an agent can pick the right kind from the task. It lacks explicit when-not/alternative-tool steering, but the mode semantics are strong enough to imply usage.

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