Grade a track record before risking capital: REAL_EDGE/REGIME_LUCK/NEGATIVE_EV. Fail-closed.
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly defined and unambiguous.
A single tool cannot exhibit inconsistency. The name 'grade_strategy' follows a clear verb_noun pattern, which is consistent with best practices.
One tool is borderline for a server focused on strategy grading. While the tool itself is well-scoped, additional tools for context (e.g., fetching strategy parameters or comparing results) might be expected, but the narrow focus is acceptable.
The tool covers the core function of grading strategies comprehensively (holdout, adjustments, significance test). However, missing auxiliary operations like listing past grades or retrieving receipts could be minor gaps for an agent.
Grade a trading/strategy track record BEFORE committing capital. Returns one verdict -- REAL_EDGE, REGIME_LUCK, NEGATIVE_EV, or INSUFFICIENT_DATA -- via chronological out-of-sample holdout, fee+slippage adjustment, and a significance test. Fail-closed. Includes a signed, independently verifiable receipt when reachable.
| Name | Required | Description | Default |
|---|---|---|---|
| agent | No | who is asking (for the receipt) | |
| trades | Yes | settled trades |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the tool is 'Fail-closed', includes a 'signed, independently verifiable receipt', and outlines the methodology (chronological holdout, fee+slippage adjustment, significance test). These are valuable behavioral traits beyond simple read-only.
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 sentences with zero waste. The primary action and key output are front-loaded, and every sentence adds value (purpose, methodology, safety/receipt).
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 2 parameters, no output schema, and no siblings, the description covers purpose, timing, methodology, the four possible verdicts, and the receipt behavior. It is sufficient for an agent to understand what the tool does and what it returns, though it could briefly explain the verdict meanings.
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%, so baseline is 3. The description adds minimal parameter detail beyond the schema; it mentions 'trades' and 'agent' but does not elaborate on their format or impact on the verdict. The schema already describes 'trades' as 'settled trades' and 'agent' as 'who is asking'.
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 uses a specific verb ('Grade') and resource ('trading/strategy track record'), and clearly states the action to be performed before committing capital. It distinguishes the tool's purpose without sibling comparison needed.
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 says 'BEFORE committing capital', providing clear context for when to use. It also mentions 'Fail-closed' as a safety property. However, it does not provide explicit when-not-to-use guidance or alternatives, though no siblings exist to contrast.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
grade_strategyFail-closed backtest/signal validation: overfitting, leakage, deflated Sharpe. NOT financial advice.
Honest A-F grades for trading strategies, backtested on real out-of-sample data. No hype.
Praxis: published trading strategies re-run and audited — verdicts, claimed vs measured stats.
Validated trading edges across futures, equities, crypto. Live signals, full audit trail.
Add one secure layer between your agents and this server.
