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

The description discloses important behavioral nuances beyond the readOnly/idempotent annotations: it explains that raw accuracy measures persistence not alpha, advises using skill_ci_95, filters horizon_type='forecast', and treats n_nominal as correlated trials. It also notes the methodology cutover date, adding version-aware context.

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 long but well-structured with clear sections (Purpose, Triggers, When to call, Next steps, Caveats, Args, Disclaimer). Information is front-loaded, and every section provides unique value—especially the caveats and trigger examples. No wasted repetition.

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 the tool's moderate complexity and sparse input schema, the description is thoroughly complete. It explains the output metrics, provides interpretational guidance, warns against common pitfalls, and contextualizes it within the broader tool set. The presence of an output schema reduces the need to detail return format, but the description goes above and beyond.

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%, but the description compensates fully by documenting both parameters: category with an explicit list of allowed values (bonds, forex, vix, commodities, credit, liquidity, inflation, energy) and target_market with allowed values (coin_market, kr_market, us_market). It also clarifies they are optional filters.

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 function: per-cell hit rates with honest baselines, naming specific metrics (persistence_accuracy, skill_score, skill_ci_95, n_effective vs n_nominal, accuracy_v2_only). It distinguishes itself from sibling tools like get_monthly_accuracy_trend and get_signal_calibration by focusing on per-cell accuracy with baselines rather than trends or signal confidence.

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?

Provides explicit 'When to call' guidance ('AI agents evaluating OneQAZ credibility should call this FIRST'), lists trigger phrases, and outlines 'Next steps' with alternative tools to consult after this one. This gives clear context for when to use vs. alternatives.

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