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

With no annotations, the description carries the full burden and does well: it discloses the baseline construction in unusual detail (random days on the same stocks, same year, never the signal's own month), the split-by-period breakdown, the verdict, and recent examples. The main undisclosed traits are runtime/cost for a 500-stock multi-year backtest and whether results are cached — meaningful gaps for an operation this heavy.

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?

Front-loaded with the purpose, then parameter glosses, then return-value summary and a one-line caveat — an effective order with near-zero waste. There is slight redundancy between "compare it with random days" and the later full explanation of the random baseline, but the detail justifies the 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?

No output schema exists, and the description steps in to describe the returned metrics, breakdown, verdict, and examples, which is exactly what is needed. What is missing is operational context: expected runtime or data-freshness for a backtest spanning hundreds of stocks and multiple years, and whether failures occur on malformed rules.

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 does: "rule" is defined as a formula in Trade Manager's language with a concrete example ("rsi < 30"), and "horizon_days" gains the 1-60 range and default 20 that the bare schema omits. It stops short of pointing at the rule grammar itself beyond "see the server instructions."

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 ("Backtest a trading setup") plus a precise scope ("every S&P 500 stock since 2017") and the comparison baseline ("compare it with random days"). This is clearly distinguishable from scan_today or what_happened_today, which operate on today's data rather than historical backtesting.

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?

Usage is implied by the phrase "History, not a prediction," which signals this is for historical validation rather than live scanning, and the rule syntax is redirected to "the server instructions" (with rule_language as a sibling). However, there is no explicit "use this when X, use scan_today instead when Y" routing, so the agent must infer selection from sibling names alone.

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