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

With no annotations at all, the description carries the full behavioral burden. It does disclose read-only status and the data source, and it names the return shape (IS/OOS metrics plus a pass/fail verdict), which is genuinely useful. However, it says nothing about runtime cost, how much history is read, whether results are persisted anywhere, or data staleness/freshness expectations for the synced candles, which matters for a tool whose validity depends on data currency.

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 compact sentences, front-loaded with what the tool does, then its output, then its data-provenance constraint. Every sentence carries information an agent needs: the table name, the read-only guarantee, the not-live-API caveat, and the strategy default. Nothing is redundant.

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 an eight-parameter, zero-required tool with no output schema, the description compensates well by summarizing return values (IS/OOS metrics, pass/fail verdict) and the data source. What is missing is guidance on valid parameter combinations, for example how lookbackBars interacts with interval or what happens when oosFraction is small, but the core invocation picture is complete.

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 all eight parameters are already documented in the schema, giving a baseline of 3. The description adds framing beyond that by naming the default strategy and confirming the universe is volume-filtered when coins are omitted, which matches the minDayVolumeUsd parameter's purpose. This is a modest but real addition over the schema.

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 FortFi research Postgres table hl_research_candles. That is far more precise than a generic 'run backtest'. It stops short of 5 because it never distinguishes itself from the clearly related sibling run_hyperliquid_research_backtest_spec or backtest_copy_trade.

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 useful context on data provenance: research-DB historical bars rather than the live HL API, which implicitly tells the agent this is for offline research. But there is no explicit when-to-use or when-not guidance and no naming of an alternative such as the _spec or copy-trade backtest variants, so the choice among siblings is left to inference.

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