Free fee-aware position sizing, net risk/reward and trade performance. Read-only, no API key.
Scored across 3 tools
Each tool targets a clearly distinct phase of the trading workflow: reviewing historical closed trades (analyze_trade_performance), evaluating a planned trade's R ratio (calculate_net_risk_reward), and sizing a position (calculate_position_size). The descriptions explicitly delineate inputs and out-of-scope items, leaving little room for misselection.
All three tools follow a consistent verb_noun snake_case pattern (analyze_trade_performance, calculate_net_risk_reward, calculate_position_size). The verbs (analyze vs calculate) accurately reflect the differing intent while the structure remains predictable.
Three tools is slightly thin but well-scoped for a focused calculator server, with each tool earning its place. The intentionally narrow scope (no leverage, liquidation, or order execution) keeps the count defensible.
The set covers the core lifecycle of risk/reward work: sizing, planned R:R, and retrospective performance analysis. Some adjacent capabilities (e.g., leverage/liquidation or scaling scenarios) are explicitly excluded, which is reasonable but leaves minor gaps.
Analyze up to 500 chronological closed trades supplied by the user, each with net P&L after costs and original risk. Returns win rate, profit factor, expectancy in currency and R, total net R, and optional closed-trade equity drawdown when initial equity is supplied. Use for reviewing an existing trade sample. No account access, deposits, intratrade drawdown, forecasts, signals, or new risk recommendations.
| Name | Required | Description | Default |
|---|---|---|---|
| trades | Yes | Closed trades ordered chronologically, all using the same currency and risk convention. Maximum 500. | |
| initialEquity | No | Starting equity before the ordered trades. Required only for equity drawdown metrics. No deposits or withdrawals are modeled. | |
| quoteCurrency | No | Currency shared by all monetary inputs. Defaults to USD; no currency conversion is performed. |
| Name | Required | Description |
|---|---|---|
| tool | Yes | |
| inputs | Yes | |
| metrics | Yes | |
| formulas | Yes | |
| warnings | Yes | |
| assumptions | Yes | |
| reproduceUrl | Yes | |
| documentationUrl | Yes | |
| calculationVersion | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false/openWorldHint=false, so the safety profile is covered. The description adds value beyond that: the 500-trade cap, the fact that drawdown is only produced when initialEquity is supplied, and explicit statements about what is not modeled (deposits, intratrade drawdown, no account access). Remaining gap is minor – no note on how missing/invalid rows are handled.
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 tight sentences: purpose+inputs, outputs, then usage and exclusions. The capability statement is front-loaded, and no sentence is filler or redundant with the name/title.
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?
An output schema exists, so return-value documentation is not required, yet the description still summarizes the metrics. With 100% schema coverage, clear annotations, and explicit in/out-of-scope boundaries, an agent has everything needed to decide and invoke correctly.
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%, and the schema already documents netPnl, initialRisk (including the 'do not substitute a later stop risk' convention), initialEquity's drawdown-only role, and quoteCurrency's no-conversion default. The description's mention of 'optional closed-trade equity drawdown when initial equity is supplied' largely restates the schema, so the baseline 3 is appropriate.
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?
States a specific verb (Analyze), the exact resource (up to 500 chronological closed trades with net P&L and original risk), and enumerates the computed outputs (win rate, profit factor, expectancy in currency and R, total net R, drawdown). This is fully distinguishable from the sibling calculators (calculate_net_risk_reward, calculate_position_size), which compute per-trade values rather than aggregate sample statistics.
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?
'Use for reviewing an existing trade sample' gives a clear activation context, and the exclusion list (no account access, deposits, intratrade drawdown, forecasts, signals, or new risk recommendations) sharply bounds when NOT to use it. It does not name a sibling alternative, but the tool set is non-overlapping, so the exclusions carry the routing burden effectively.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compare gross and fee-adjusted reward-to-risk, loss and profit per unit, and breakeven win rate for a linear trade with known entry, stop and target. Accepts distinct entry/stop/target fee percentages. Use for questions about a planned R ratio or how fees change it. Direction is derived from entry and stop. Does not fetch venue fees or predict execution, liquidation, or trade outcomes.
| Name | Required | Description | Default |
|---|---|---|---|
| fees | No | User-supplied rates. Omission explicitly assumes zero fees; no exchange rate lookup is performed. | |
| stopPrice | Yes | Planned stop price. Direction is derived from entry and stop. | |
| entryPrice | Yes | Planned entry price in quote currency per base unit. | |
| targetPrice | Yes | Profit target price, opposite the stop relative to entry. | |
| quoteCurrency | No | Currency shared by all monetary inputs. Defaults to USD; no currency conversion is performed. | |
| instrumentType | No | Linear quote-margined instruments only. Inverse contracts and liquidation are unsupported. |
| Name | Required | Description |
|---|---|---|
| tool | Yes | |
| inputs | Yes | |
| metrics | Yes | |
| formulas | Yes | |
| warnings | Yes | |
| assumptions | Yes | |
| reproduceUrl | Yes | |
| documentationUrl | Yes | |
| calculationVersion | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). Beyond that, the description discloses scope limits – no venue fee lookup, no execution/liquidation/outcome prediction – and the zero-fee assumption on omission, which is genuinely useful context an agent could not infer from annotations alone.
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?
Front-loaded with the core computation, then assumptions, then exclusions in a compact run of sentences with no filler. Some content duplicates what the schema already states, which slightly dilutes the value of each sentence.
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 tool is moderately complex (6 params, nested fees), and the description supplies direction derivation, fee-assumption behavior, and unsupported operations. With annotations, full schema coverage, and an output schema handling return values, the description is essentially complete for correct invocation.
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 the schema already documents every parameter, including the fee nesting and the entry/stop direction derivation. The description largely restates those same facts (distinct fee percentages, direction from entry/stop) without adding new semantics, so the baseline 3 applies.
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?
States specific computations (gross and fee-adjusted reward-to-risk, loss/profit per unit, breakeven win rate) for a well-defined object (a linear trade with known entry, stop, target). This is clearly differentiable from calculate_position_size and analyze_trade_performance without opening any schema.
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?
Gives explicit when-to-use ("Use for questions about a planned R ratio or how fees change it") and explicit exclusions ("Does not fetch venue fees or predict execution, liquidation, or trade outcomes"). It stops short of naming the sibling tools as alternatives, so it misses the top mark.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Calculate position quantity and notional for a linear crypto futures trade from user-specified account balance, risk percentage, entry and stop. Includes separate entry/stop fees and optional target profit and net R. Direction is derived. Use when asked how much to buy or sell for a specified risk budget. Ask for missing prices or risk preference; do not invent them. Does not calculate liquidation, leverage, inverse contracts, exchange lot rounding, signals, or execute orders.
| Name | Required | Description | Default |
|---|---|---|---|
| fees | No | User-supplied rates. Omission explicitly assumes zero fees; no exchange rate lookup is performed. | |
| stopPrice | Yes | Planned stop price. Direction is derived from entry and stop. | |
| entryPrice | Yes | Planned entry price in quote currency per base unit. | |
| riskPercent | Yes | User-chosen account risk percentage, e.g. 1 means 1%. Never infer a risk preference. | |
| targetPrice | No | Optional profit target, opposite the stop relative to entry. | |
| quoteCurrency | No | Currency shared by all monetary inputs. Defaults to USD; no currency conversion is performed. | |
| accountBalance | Yes | Account balance in the same quote currency as prices. | |
| instrumentType | No | Linear quote-margined instruments only. Inverse contracts and liquidation are unsupported. |
| Name | Required | Description |
|---|---|---|
| tool | Yes | |
| inputs | Yes | |
| metrics | Yes | |
| formulas | Yes | |
| warnings | Yes | |
| assumptions | Yes | |
| reproduceUrl | Yes | |
| documentationUrl | Yes | |
| calculationVersion | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavioral context beyond them: omitted fees mean zero fees with no exchange lookup, direction is derived from entry/stop, no lot rounding, no inverse/liquidation support, and a do-not-invent policy for prices and risk. This is rich disclosure of scope limits and input defaults.
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?
Front-loaded with what is calculated and from what inputs, then usage, then exclusions. Every sentence carries a distinct constraint; no filler or redundancy across purposes.
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?
An output schema exists, so return values needn't be explained, and the schema fully documents inputs. Combined with the description's scope limits, usage trigger, and input policy, an agent has everything needed to invoke it correctly.
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 the schema already documents all 8 parameters, including fee percentages, defaults, and 'never infer a risk preference'. The description mainly restates those same facts ('direction is derived', 'do not invent' risk), adding little semantics beyond the structured fields, so baseline 3 applies.
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?
States a specific verb and resource: computing position quantity and notional for a linear futures trade from balance, risk %, entry and stop. The trigger 'how much to buy or sell for a specified risk budget' is clear. However, it never names or contrasts with the sibling calculate_net_risk_reward, and it advertises a 'net R' output that could be conflated with that sibling.
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?
Gives an explicit when ('asked how much to buy or sell for a specified risk budget') and an explicit when-not list (no liquidation, leverage, inverse contracts, lot rounding, signals, order execution). It also directs the agent to ask for missing inputs rather than infer them. Alternatives are not routed to explicitly, so sibling differentiation is missing.
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.
analyze_trade_performancecalculate_net_risk_rewardcalculate_position_sizeRead-only crypto indicators, risk sizing and rule backtests. Not financial advice.
Instant "can I take this trade?" check against prop firm drawdown/position/consistency rules.
Read-only crypto and traditional portfolio: holdings, PNL, FIFO tax figures and market data.
Sourced prop-firm daily-loss and max-drawdown rules and a drawdown-room checker. Read-only, no auth.
Add one secure layer between your agents and this server.