Is a trading strategy's track record luck? Free luck check, plus what a full strategy audit checks.
Scored across 2 tools
The two tools serve entirely distinct purposes: one explains the audit service (how it works, pricing, etc.) while the other performs a specific statistical test on a strategy's track record. No ambiguity in selection.
Both tool names follow a clear verb_noun pattern (explain_audit, luck_check), with consistent lowercase and underscore separation. The naming clearly indicates the action and target.
With only two tools, the server feels minimal. While the scope is narrow (auditing trading strategies), the count is borderline—one core function plus a documentation tool is thin, but not entirely unreasonable for a niche service.
The domain implies a full audit service, but the tool surface only provides a description and a rough luck check. There is no tool to actually run the complete audit, upload data, or access detailed reports, leaving significant gaps that would prevent an agent from completing the core workflow.
Describes a full Autrady audit of a strategy's actual signals: what to upload, how it works, the five questions it answers with what each caught in Autrady's own research, the price, the free trial and where to start. Use it when someone asks how to test a bot, a newsletter or a backtest properly, what Autrady does, or what it costs.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds behavioral context by explaining what the tool covers (upload process, how it works, five questions, pricing, free trial, starting point), which goes beyond the annotations. It doesn't contradict 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?
The description is a single, information-dense sentence that front-loads the core purpose ('Describes a full Autrady audit') and then lists the key aspects. It's efficient and covers all necessary points without excessive verbosity. The usage guidance is appended naturally at the end.
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?
For a no-parameter, read-only informational tool, the description is complete. It covers what the tool does, what it includes, and when to use it. The lack of an output schema is acceptable since the description explains the content. The sibling tool 'luck_check' is different enough that no further differentiation is needed.
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?
The tool has zero parameters, so the schema provides no parameter details. The description compensates by explaining the tool's content and scope, which is sufficient for a no-parameter informational tool. The baseline for 0 params is 4, and the description meets that by providing clear context about what the tool returns.
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 the tool's purpose: describing a full Autrady audit, including what to upload, how it works, the five questions it answers, pricing, free trial, and where to start. It uses a specific verb ('describes') and resource ('Autrady audit'), and distinguishes itself from the sibling tool 'luck_check' by focusing on audit details rather than luck checking.
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 states when to use the tool: 'Use it when someone asks how to test a bot, a newsletter or a backtest properly, what Autrady does, or what it costs.' This provides clear usage context and implicitly distinguishes it from alternatives like 'luck_check' by focusing on audit-related queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tests whether a trading strategy's claimed track record could be luck. Returns how often the best of that many strategies with no edge at all would look this good, the record's t-statistic against the bar for that many tries, and how many months a real edge of this size needs to clear the bar with 80% probability. A rough check: it assumes independent months and ignores costs, so a real audit of the signals usually looks worse.
| Name | Required | Description | Default |
|---|---|---|---|
| months | Yes | Months of results in the track record, from 2 to 1200. | |
| versionsTried | No | How many versions or variations were tried before this one was picked. If unknown, use 10. | |
| monthlySwingPercent | Yes | Typical monthly swing: the standard deviation of monthly returns, in percent. Stock strategies usually sit between 4 and 8. | |
| averageMonthlyReturnPercent | Yes | Average return per month, in percent. 1.5 means +1.5% a month. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this read-only, idempotent, and non-destructive. The description adds genuinely useful behavioral context beyond those flags by disclosing the model assumptions: independent months, no costs, and that 'a real audit of the signals usually looks worse.' That is important for calibrating trust in the result.
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 sentences front-load the main action, then the outputs, then the caveat. Every sentence earns its place and there is no repeated information from the schema or annotations.
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?
With no output schema, the description responsibly names the three return values and their interpretive meaning. It also includes the assumptions and limitations needed to use the result correctly; it only omits explicit guidance on when to escalate to the sibling audit 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 description coverage is 100%, so all four parameters are already explained in the input schema; the baseline is therefore 3. The description's conceptual phrases like 'that many strategies' and 'edge of this size' map loosely to versionsTried and the return inputs, but they do not add details about the parameters beyond what the schema provides.
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 object: 'Tests whether a trading strategy's claimed track record could be luck,' and it enumerates the three statistical outputs. It is clear on its own, but it does not explicitly contrast itself with the sibling explain_audit, so an agent must infer the boundary between a luck check and an audit.
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 final sentence provides an implicit usage context: this is 'a rough check' whose assumptions make results look better than a real audit. That implies use as a preliminary screen rather than a substitute for audit, but the description does not explicitly say when to choose luck_check over explain_audit or what conditions should route to the sibling.
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.
explain_auditluck_checkTells you whether a trading strategy's edge is distinguishable from luck.
Grade a track record before risking capital: REAL_EDGE/REGIME_LUCK/NEGATIVE_EV. Fail-closed.
Praxis: published trading strategies re-run and audited — verdicts, claimed vs measured stats.
Honest A-F grades for trading strategies, backtested on real out-of-sample data. No hype.
Add one secure layer between your agents and this server.
