Leaderboard

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

Beyond the annotations, the description discloses that data is batch-computed, that an error is returned if no batch run exists, and that farmer_flag is heuristic ('v0'). It also clarifies field semantics like 'USD where monetary' and day_winrate as 'pct 0-100', which materially helps an agent interpret results.

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 dense but front-loaded: the first sentence establishes the core purpose, and the error contract and example are practically useful. Some repetition with the output schema exists in the column list, but there is no filler.

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 an output schema and annotations present, the description covers the non-obvious context: batch-run dependency, error behavior, heuristic farmer flags, and metric options. The main gap is that the metric parameter's effect on the leaderboard is not explicitly defined, but the example partially compensates.

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 0%, so the description must compensate, but it only lists the metric enum values and gives an example. It does not explain what the metric parameter controls (sorting? selecting?), nor does it describe limit or offset semantics beyond what their names and defaults imply.

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 opens with 'Verified trader leaderboard from our registry + PnL engine (batch-computed)' and enumerates the rows returned, so the resource and aggregation nature are clear. It does not explicitely name a sibling like trader_pnl_stats or list_traders to contrast with, but the batch-computed leaderboard scope makes it distinguishable enough.

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?

It gives a concrete precondition — 'Requires a batch run — otherwise returns {error}' — and a valid example invocation. However, it never states when to prefer this tool over alternatives such as trader_pnl_stats or list_traders, nor gives when-not-to-use guidance.

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