backtest

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

With no annotations, the description carries the full burden but does not say whether this is a read-only computation or whether it persists results, nor whether it requires a completed run or imported actuals to exist. It discloses only the output dimensions (correlation, winner match, calibration) and nothing about side effects, errors, or cost.

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 with the action front-loaded and the metric list appended; no filler. It stops short of five only because the compactness comes at the cost of the missing prerequisite and parameter detail.

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 3-parameter, annotation-free tool with no output schema, the description does useful work by naming the returned metrics. But it omits the purpose of 'map', the prerequisite that ads_import/actuals_import must have run, and whether a run must be finished — gaps an agent would need to resolve by trial.

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 0% across 3 parameters. The description implicitly covers 'run' and 'actuals' (real ad results from ads_import) but says nothing at all about the 'map' parameter, which is entirely undocumented in both schema and prose. Partial compensation is not enough at this coverage level.

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 ('Score') and resource ('a run's feed test against real ad results'), and enumerates the metrics produced (rank correlation, winner match, calibration), so the agent knows exactly what the tool computes. It does not explicitly distinguish itself from the sibling holdout_backtest, which is a similar scoring tool, leaving that differentiation to the agent.

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?

The parenthetical '(from ads_import)' hints at the prerequisite source for actuals, which implies a call ordering. However, there is no explicit statement of when to use this versus holdout_backtest, and no exclusions or preconditions beyond that hint.

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