backtest_plan

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

With no annotations, the description carries full behavioral burden. It discloses that missing price data buckets are reported rather than invented and that this is a past replay, not a forecast. It could also state side effects, rate limits, or output normalizations, but the core non-destructive, non-inventive behavior is well conveyed.

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, front-loaded with the action and expected outputs. Each sentence adds useful information: what it does, how missing data are handled, and a caveat about interpretation. No wasted words.

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?

This is an 11-parameter tool with no output schema and no annotations. The description gives a high-level summary and a data-fidelity promise, but it does not cover parameter behavior, return structure, failure modes, or how the plan rules are applied. An agent would still have significant uncertainty when invoking it.

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 only 27%, and the description does not compensate. It mentions fee-related outputs but does not explain period, fixed_fee_eur, max_fee_ratio, rebalance_band_abs, contribution_every_months, or price_source semantics. The schema only documents targets, tickers_by_bucket, and price_source, leaving most parameters without meaningful guidance.

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: replaying plan rules on past monthly prices, and lists concrete outputs (fees paid, drift, drawdown, final weights). It does not explicitly distinguish itself from sibling backtest_picker, so it falls short of the top score, but the purpose is unambiguous.

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 description implies when the tool is appropriate: when a historical replay of plan rules is needed, and it explicitly says it is not a forecast. However, it does not name alternatives, exclusions relative to sibling tools, or prerequisite situations, so guidance remains mostly implicit.

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