Prediction Scorecard

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

The description adds significant behavioral detail beyond annotations: it flags a likely regime change when realized win rate falls 10 percentage points or more below predicted, and recommends re-measuring signal statistics. This gives the agent concrete expectations about outputs and side effects (recommendations), which the annotations' readOnly/idempotent hints do not convey.

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-load the main purpose, then add actionable details and value. No filler words, and each clause contributes meaning. Well-structured for quick parsing.

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?

Given zero parameters and an output schema that likely details return fields, the description completely covers what the tool does, when to use it, and what behavioral triggers to expect. It also conveys the broader purpose of keeping recommendations honest. Nothing important seems missing.

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 schema has zero parameters, so the baseline is 4. The description correctly focuses on behavior rather than parameter details, and there are no parameters to explain. It adds value by clarifying what the tool does internally.

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 scores past setups from top_setups against actual outcomes, with specific outputs like hit/miss and calibration. It distinguishes itself from siblings like learned_winrates and top_setups by focusing on retrospective evaluation rather than setup generation or rate lookup.

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 implies when to use the tool—after setups have played out—and describes its role as a feedback loop. While it doesn't explicitly name alternatives or exclusions, the context is clear enough for an agent to know it is for periodic performance review rather than for setting up new trades.

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