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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds real context: re-backtesting on exact ticks, the distinct evaluation horizons (7 days for net_apr, 24 hours for burst), and the shape of the result (counts, share positive, median APR at signal vs realised, worst case).

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?

A single dense sentence covers scope, method, horizons, and outputs with little waste. The phrasing 'How past opportunity signals really did' is slightly colloquial and requires a re-read, but it is compact and front-loaded.

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?

With no output schema, the description usefully enumerates the returned metrics, and both optional parameters are fully documented with defaults in the schema. It is complete enough to call correctly, though a note on the lookback vs horizon interaction (days=30 but 7-day evaluation) would help.

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 baseline is 3, but the description adds meaning the schema does not: the per-kind evaluation horizon (7 days for net_apr, 24 hours for burst) explains what 'kind' actually changes. The 'days' lookback and default are already in 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?

The description names the resource (past opportunity signals) and the specific operation (re-backtesting them on their exact ticks after the fact), which is clearly distinct from list_signals or backtest_range conceptually. It never names a sibling outright, so an agent must infer differentiation, keeping it below 5.

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?

There is no explicit when-to-use guidance, no exclusions, and no mention of the sibling backtest_range, which sounds like an adjacent capability. The agent can infer that this is a retrospective accuracy check, but nothing states when this beats alternatives.

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