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

Annotations already declare safe read-only/idempotent behavior; description adds substantive methodology (net of fees, SPY/BTC benchmark, two windows, +20% hit rate) and that a caveat is always attached. It still omits return shape and limitations of the backtest, but adds real value.

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?

One dense sentence with no filler; operation and modes are front-loaded. Parenthetical details are compact but make parsing slightly harder.

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 multi-parameter backtest tool with no output schema and no annotations beyond safety, the description covers methodology and basket selectors. It leaves prerequisites (e.g., exactly which params must be combined), output/return expectations, and backtest limitations under-specified.

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 description must carry parameter meaning. It maps basket_id, symbols+asset_class, and theme to three basket-specification modes, but does not explain formats/valid values/defaults or that they are alternative optional paths.

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 operation (walk-forward 90-day backtest) and resource (basket), and enumerates three ways to specify the basket. It does not explicitly distinguish itself from backtest-related siblings such as list_backtest_surfaces or get_backtest_models, so not a 5.

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?

Describes three input modes (basket_id, symbols+asset_class, theme rule basket), which implies when each form is used, but gives no explicit when-to-use vs alternative tools or prerequisites/constraints. “no key needed” is a small usage note but not selection guidance.

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