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

Beyond annotations (readOnlyHint, idempotentHint), the description discloses the full experimental design: selection-window ranking, subperiod checks, embargo, held-out performance reveal, doubled costs as a stress test, buy-and-hold comparison, and deflated Sharpe correction for multiple trials. This is rich behavioral context that annotations alone do not provide.

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 purpose and usage guidance, then detailed methodology. The third sentence is a dense list but each item earns its place; minor redundancy exists with the schema's symbols description that already mentions deflated Sharpe accounting. Efficient overall for a complex tool.

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?

For a 14-parameter research tool with no output schema, the description thoroughly explains methodology and purpose but leaves the output format implicit. An agent can infer that results include rankings and held-out performance, but explicit return-value documentation would make it complete.

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 86%, so the schema carries most parameter semantics. The description adds cross-parameter context (every strategy/symbol/timeframe combination is a trial, corrected by deflated Sharpe) but does not substantially elaborate individual parameter meanings beyond the schema. Baseline 3 is appropriate.

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+resource: runs one chronological research experiment across many built-in strategies, instruments, and timeframes. It explicitly distinguishes itself from backtest_run by naming the anti-pattern of testing one strategy on coin after coin, making sibling differentiation clear.

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?

Explicitly directs use to broad discovery and says to use it instead of many backtest_run calls, even naming the exact anti-pattern it replaces. The description gives a clear when-to-use instruction and identifies the alternative tool, matching the top-tier calibration.

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