pro_replay

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

With no annotations, the description carries the full burden. It does disclose useful behavior: execution reads straight off memory-mapped columns, and the result is byte-equivalent to replay_orders. It says nothing about the fills_csv input, error behavior for a missing/mismatched dataset, or cost of a replay run.

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 compact sentences, front-loaded with the Pro marker and the core action, with no filler. The parenthetical column list is dense but earns its place by defining the CSV format.

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 three-parameter tool with no output schema, the description covers the essential call path end-to-end: where the dataset name comes from and what the output will look like (same as replay_orders). The main gap is the optional fills_csv parameter, whose role is never explained.

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 0%, so the description must compensate, and it partially does: orders_csv is defined by its columns (time, side, qty) and dataset by its provenance and naming convention. The third parameter, fills_csv, is never mentioned and its purpose (optional fill data?) is completely 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?

States a specific verb and resource: replay an orders CSV (with its time/side/qty shape) against a dataset produced by pro_sync, and notes the output is identical to replay_orders. That distinguishes it from the plain replay_orders sibling, though the distinguishing axis (Pro / memory-mapped performance) is only implied rather than spelled out.

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 supplies a real prerequisite: the dataset must be the name returned by pro_sync, with a concrete example ("BTCUSDT-aggTrades"). But it never says when to pick pro_replay over replay_orders despite the two producing the same output, so the choice between siblings is left to inference.

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