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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses concrete behavior: equal-weight long/short portfolios, next-bar-open entry and following-bar-open exit, re-screening each bar, and turnover-based cost calculation so unchanged holdings are not double-charged. This is rich, non-obvious behavioral detail.

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 with no filler: the mechanism is front-loaded, the usage condition follows, and the cost nuance earns its place. Every sentence contributes distinct value.

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 complex 12-parameter backtest tool, the description plus a well-covered schema and strong annotations gives an agent everything needed to select and invoke it correctly. The absence of an output schema is acceptable because the description focuses on behavior needed before calling, and the schema documents the parameters.

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 high (83%), so the baseline is 3, but the description adds meaningful parameter-level context: 'equal-weight' clarifies maxPositions behavior, 'long or short' ties to direction, and the turnover-cost sentence clarifies how feeBps actually applies. It doesn't document each parameter, but it adds interaction semantics the schema lacks.

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 opens with a specific verb and resource: 'Historically replay a cross-sectional screen at every bar,' then details the portfolio construction, entry/exit timing, and re-screening process. It explicitly distinguishes itself from a single-symbol backtest, so an agent can tell it apart from siblings like backtest_run.

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 gives an explicit use case: 'Use this when the question is whether repeatedly trading screener matches worked.' It also states what is not a substitute — a single-symbol backtest of coins that match today — providing clear when-not guidance.

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