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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds the decisive behavioral fact those annotations cannot convey: FULL TIER ONLY, and this free endpoint returns UPGRADE_REQUIRED with token instructions. It also notes buy-and-hold is returned alongside, which shapes expected output. It stops short of describing result contents, but an output schema exists.

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 tight sentences with the most decision-relevant constraint (FULL TIER ONLY) front-loaded, followed by the use case and the free fallback. No filler or repetition of the title.

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 gated, zero-param tool with an output schema, the description supplies everything needed to decide whether to call it and what to expect if it is called on the free endpoint. Only the mechanism for supplying strategy/asset (absent from the schema) is left implicit.

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?

With zero parameters there is nothing for the description to clarify, so the baseline applies. The description does not attempt to invent parameters, which is consistent with the empty schema, though the implied strategy/asset selection remains unexplained.

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: run a strategy's rules over an asset's real price history, plus a buy-and-hold baseline. This clearly separates it from backtest_integrity and the portfolio/stress siblings. The only muddiness is that the tool takes zero parameters yet describes acting on 'a strategy' and 'an asset', leaving the implied input source unexplained.

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?

Gives a when-to-use condition ('when you want a strategy's rules run on real history') and names the concrete alternative, backtest_integrity, for checking an existing backtest for overfitting. A when-not statement beyond the tier gate would push this to a 5, but the routing is unambiguous.

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