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

With no annotations supplied, the description carries the full burden and does well: it explicitly declares the operation read-only, discloses that bars come from synced Postgres history instead of the live Hyperliquid API, and describes the return (IS/OOS metrics and a pass/fail verdict). It still omits runtime expectations, whether results are persisted anywhere, and what happens when stored data is missing or stale.

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 short sentences with zero filler: purpose first, then return contract, then the read-only/data-source caveat, then the strategy note. Each sentence carries distinct information an agent needs, and nothing is repeated from the schema at length.

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?

There is no output schema, and the description compensates by naming the returned metrics and verdict, which is the key unknown for a backtest tool. With 8 optional parameters fully documented in the schema, the remaining gap is minor: it does not address data-availability preconditions or expected execution time for a potentially heavy compute call.

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 100%, so every parameter including defaults and enums is already documented in the schema. The description adds only a restatement that momentum_cross is the default strategy, which duplicates the schema entry; it adds no new semantics such as how oosFraction interacts with lookbackBars or how the volume floor applies when coins is omitted.

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 an out-of-sample backtest on Hyperliquid perp OHLCV from the hl_research_candles table in FortFi research Postgres. It also names the return shape (IS/OOS metrics plus pass/fail verdict). It does not distinguish itself from the close sibling run_hyperliquid_research_backtest_spec, which an agent could easily confuse with this tool.

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?

Usage is implied rather than stated: the description clarifies the data source is synced historical bars rather than the live HL API, which helps an agent pick it for research rather than live checks. However, it never says when to prefer this tool over run_hyperliquid_research_backtest_spec, get_hyperliquid_research_data_stats, or the live market tools, and gives no prerequisites such as requiring prior data sync.

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