Learned Signal Win Rates

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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false), the description richly explains the mechanism: it records every firing signal across top-volume coins, grades them against actual outcomes, builds a real-world database over time, and notes it's measured live performance, not backtest. This adds substantial value over the annotations and discloses the early-empty behavior.

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 two sentences, front-loaded with the core purpose, and every phrase adds value (e.g., 'whether or not it traded them', 'not backtest', 'Empty early on'). It packs substantial information into a compact, readable format without redundancy.

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?

The tool is a read-only informational query with low complexity, and the output schema presumably covers return structure. The description explains the data's provenance, reliability, and evolution over time. However, the missing explanation of the 'top' parameter leaves a small but real gap in the overall description's completeness.

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?

The input schema has 0% description coverage for the only parameter 'top', and the description does not mention it at all. While 'top' likely relates to the number of win rates to return, the description does not clarify its meaning or effect. The default of 15 mitigates the issue, but the lack of any explanation is a notable gap.

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 states the tool shows signal win rates 'LEARNED from continuous observation' and explicitly contrasts with backtesting ('not backtest'), making it distinct from potential siblings like learned_combos. The verb 'Show' plus the resource 'signal win rates' is specific and unambiguous.

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 clear context on when to expect meaningful data ('Empty early on; fills up as the autonomous loop runs') and an explicit exclusion ('not backtest'), but it does not name alternative tools or provide when-not-to-use guidance beyond that. This is strong but not fully explicit about alternatives.

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