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

Annotations already declare readOnlyHint and openWorldHint, yet the description adds genuinely new behavior: no fund movement, no Diary writes, empty-list semantics for unimplemented venues, and loud failure rather than silent truncation on timeout. The truncation-vs-error distinction is exactly the kind of non-obvious trait that prevents an agent from misreading an empty result as 'no activity'.

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?

Three sentences, front-loaded with the READ-ONLY marker and the core action before the caveats. Dense with em-dash asides, but each clause carries distinct information; only the 'never writes Diary rows' clause borders on internal trivia.

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?

No output schema exists, so the description takes on return-shape duty and does partially discharge it by describing rows as executions with price/qty/fee. Pagination beyond the limit cap and the exact row fields are left implicit, a minor gap for a six-parameter read tool.

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% and the schema already documents lookback bounds, newest-first limit, the spot/futures/all enum, and connectionId precedence over exchange. The description reinforces the spot+futures scope and the 'CEX connection' concept but adds no format or precedence detail beyond the schema, so the baseline 3 applies.

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?

Names a specific verb and resource ('list recent execution fills on a CEX connection') and pins down the unit of data ('individual order executions with price/qty/fee, spot + futures'). It also explicitly separates itself from the nearest sibling by pointing PnL questions at read_closed_pnl.

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 a clear use case (Activity history of fills) and an explicit routing rule away from this tool for realized PnL ('see read_closed_pnl'). It does not address ordering-vs-fills questions such as list_open_orders or cancel_order, but the primary alternative is named with its selecting condition.

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