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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), yet the description still adds real simulation semantics: fill timing at next-bar open, one-bar holding, and that costs track actual turnover so a carried position is not charged a fresh round trip. It omits practical cost concerns such as runtime for large lookback × universeSize combinations.

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?

Four tight sentences with the core mechanic front-loaded, followed by the routing discriminator and the cost-model caveat. Nothing is redundant with the title or schema.

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 tool with no output schema, the description explains the strategy construction well but never indicates what comes back (equity curve, returns, hit rate, per-trade list) or how lookback and universeSize affect runtime and result length. Adequate but leaves a real gap around the return value.

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 nearly every parameter is already documented in structured data; the description's only added meaning is that slots are equal-weight (maxPositions) and that costs are per side applied to turnover (feeBps/slippageBps). It adds nothing about rules, universeSize, or manualSymbols 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 and resource — historically replaying a cross-sectional screen at every bar — and spells out the mechanics (equal-weight long/short, entry at next bar open, held to the following bar open, then re-screened). This is clearly distinguishable from screener_run (single point-in-time screen) and backtest_run (single-symbol).

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 says when to use it ("when the question is whether repeatedly trading screener matches worked") and names the wrong alternative in generic terms ("a single-symbol backtest of coins that match today is not a substitute"). It stops short of naming the sibling tools backtest_run or screener_run, so routing is inferred rather than stated.

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