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

Annotations declare readOnlyHint, and the description goes further by explicitly stating it does not change ranking weights or the threshold 55, and that forward returns are computed on-demand from klines rather than precomputed columns. It also discloses operational limits like default/max rows. It does not describe the exact output shape, but it communicates key behavioral expectations.

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?

The description is a dense paragraph with no filler, and the core action is front-loaded. It repeats a few schema defaults, but every sentence contributes either behavioral transparency or operational context.

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?

Given 7 parameters, two enums, and no output schema, the description covers the data source, computation window, filters, aggregation, limits, and non-mutating nature. It does not enumerate exact return fields, but the aggregation statement gives enough shape for an agent to call the tool successfully.

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 coverage is 100% and each parameter already has a useful description, so the baseline is 3. The tool description mostly restates limit and forwardWindow behavior, adding only minor extra context such as 'setiap row 1 kline lookup'. It does not substantially improve on 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 opens with a specific verb and resource: forward-testing decisions stored in `pipeline_decision_log`. It enumerates the exact computations (forward return, stop-loss touch) and aggregation dimensions (decision type, score bucket), which clearly distinguishes it from pipeline execution or generic signal backtest siblings.

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 tool's intended use is strongly implied by 'Uji maju keputusan yang tersimpan di pipeline_decision_log' and the on-demand framing, but the description never explicitly names alternatives or states when to prefer this over `whalescope_full_pipeline` or `binance_backtest_signal`. Guidance is implicit, not explicit.

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