Retrieve historical backtest performance for specified models or all models. Uses dynamic classification thresholds and returns null for missing fields for accurate model evaluation.
讀取歷史 backtest 績效（model 空白 = 全部）。
分類指標不再硬用 50% 門檻：baseline_threshold = max(majority_class_baseline, uniform_random_baseline)。
沒有資料的欄位回 null（不是 0）。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| model | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description takes on the full burden of behavioral disclosure. It meaningfully discloses the classification threshold rule (baseline_threshold = max of two baselines) and the null-return behavior for missing fields, both of which go beyond what a generic read operation implies. It does not describe the return format, but the disclosed behaviors are substantial and non-obvious.
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 three short sentences with no filler. The core purpose is front-loaded, and each subsequent sentence adds distinct behavioral value: model blank handling, threshold logic, and null semantics. Every sentence earns its place.
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?
The description covers key filter semantics and two important behavioral quirks, but the absence of both annotations and an output schema means more burden falls on the description. It does not specify the response shape, how limit interacts with results, or how this tool relates to performance-related sibling tools. Enough for basic use, but not fully 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 0%, so the description must compensate. It explains the 'model' parameter's empty-means-all behavior, which is valuable, but it gives no semantic guidance for the 'limit' parameter beyond its schema default. With only one of two parameters clarified, the coverage is incomplete.
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 states a clear verb-resource pair: '讀取歷史 backtest 績效' (read historical backtest performance). It clarifies an important scope condition ('model 空白 = 全部'), but it does not explicitly distinguish this tool from siblings like get_model_leaderboard or get_forward_test_status, so it falls slightly short of a 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?
The description gives no guidance on when to choose this tool over alternatives such as get_model_leaderboard or backtest. It mentions the 'model blank = all' behavior, which is parameter usage rather than tool-selection guidance. No exclusions or alternative routing is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.