Head-to-head comparison of two strategy templates from real monthly engine runs across ~50 coins: per-coin win count, median out-of-sample Sharpe, survival counts, median return and drawdown. Use strategy names from list_strategies (e.g. 'super_trend', 'ema_crossover').
| Name | Required | Description | Default |
|---|---|---|---|
| strategy_a | Yes | First strategy name, e.g. super_trend | |
| strategy_b | Yes | Second strategy name, e.g. ema_crossover |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description doesn't need to re-state safety. It adds valuable context about the data source (real monthly engine runs) and output metrics, enhancing transparency beyond the annotations.
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?
Two concise sentences: first states the purpose and scope, second lists the metrics. No wasted words or redundant information.
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 the tool's function, data source, and output metrics. Given no output schema, listing the metrics is sufficient. It does not explain aggregation details, but overall completeness is adequate for a comparison tool.
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%, providing a baseline of 3. The description adds value by giving concrete examples ('super_trend', 'ema_crossover') and directing users to list_strategies for valid names, which significantly aids parameter understanding.
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 clearly states it performs head-to-head comparisons of strategy templates, specifying the data source (real monthly engine runs across ~50 coins) and the exact metrics computed (win count, Sharpe, survival counts, return, drawdown). It distinguishes itself from siblings like list_strategies by referencing it as the input source.
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 explicitly advises using strategy names from list_strategies, providing clear context for input selection. While it doesn't explicitly state when to avoid using this tool or suggest alternatives, the reference to a sibling tool gives implicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: statistical checks, strategy comparison, historical returns, live signals, DCA, overfitting index, strategy listing, dataset query, backtesting, Q&A search, and glossary. No overlap in functionality.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., check_overfitting, run_backtest, search_glossary). No mixing of conventions.
11 tools is well-scoped for a crypto backtesting server, covering the full workflow from strategy selection, backtesting, overfitting analysis, to educational queries without excess or deficiency.
The tool set covers core backtesting, overfitting diagnostics, data retrieval, and knowledge base searches. Minor gaps like strategy modification or saving results are present, but the main lifecycle is complete.
