bitbank-mcp-server

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v0.1.1
Disambiguation5/5
Each tool targets a specific technical indicator, data source, or analysis task with clear, non-overlapping descriptions. For example, Bollinger Bands, EMA, SMA, Stochastic, Ichimoku, and Fibonacci each have dedicated snapshot tools, while higher-level tools like analyze_indicators and analyze_market_signal provide composites. Overlap is minimal and explicitly noted (e.g., snapshots vs. chart data).
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern: verbs like analyze_, detect_, get_, prepare_, render_, run_, refresh_, validate_ are used systematically. The noun part clearly indicates the object (e.g., bb_snapshot, candle_patterns, currency_strength, orderbook). No mixed conventions or vague verbs.
Tool Count4/5
With 32 tools, the server is comprehensive but slightly heavy. Each tool serves a distinct purpose in trading analysis, from indicator snapshots to backtesting and data validation. However, the count is on the higher end of reasonable; a few tools (e.g., multiple snapshot tools) could potentially be consolidated, but the scope justifies the number.
Completeness5/5
The tool surface covers the full lifecycle of technical analysis: data retrieval (get_candles, get_ticker, get_transactions), indicator analysis (snapshots and composite), pattern detection, order book analysis, flow metrics, backtesting, charting (SVG/PNG), and data quality validation. There are no obvious gaps for a typical trading analysis workflow.
Average 3.6/5 across 32 of 32 tools scored. Lowest: 2.4/5.
See the Tool Scores section below for per-tool breakdowns.
- 1 of 2 community issues answered or closed in the last 6 months
- 332 commits in the last 12 weeks
- Last stable release on July 6, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility for disclosing behavioral traits. It mentions the output (alignment direction and confluence) but fails to indicate whether the tool is read-only, requires authentication, or has any side effects. This is insufficient for a tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise, consisting of a single line that front-loads the key concept. However, it is slightly too brief; a structured overview with separate sections for purpose and output would improve readability without adding significant length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of multi-timeframe SMA analysis and the absence of an output schema, the description is severely incomplete. It does not define 'alignment direction' or 'confluence', nor does it explain how periods and timeframes interact. Compared to sibling tools like analyze_mtf_fibonacci which likely have richer descriptions, this is insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not explain any of the three parameters (pair, periods, timeframes). Schema description coverage is 0%, and the description adds no semantic meaning beyond the parameter names visible in the schema. As a result, the agent has no understanding of what values to provide.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool analyzes multi-timeframe SMA and determines alignment direction and confluence. It uses specific terms like 'Multi-Timeframe SMA' and 'MTF' which convey the resource and verb. However, it does not explicitly differentiate from sibling tools like analyze_sma_snapshot, leaving room for ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or context for usage. It simply states what the tool does without any usage recommendations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It mentions the method (order book and candlesticks) and states 'speculation-based', indicating non-precision. However, it does not disclose whether the tool is read-only, destructive, requires authentication, or has rate limits. The behavioral impact is poorly communicated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (two lines) and front-loaded with a helpful bracket keyword summary. However, it sacrifices clarity for brevity; every sentence earns its place but lacks necessary detail. It is concise but under-informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain return values (e.g., detected events, confidence metrics). It only mentions 'detection' without specifying output format or behavior. For a detection tool, this is incomplete; an agent cannot reliably interpret the result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameter description coverage is 0%. The description does not explain the meaning of 'pair', 'minSize', or 'lookback' beyond their names and schema defaults. For example, 'minSize' likely refers to minimum order size in BTC, but this is not stated. The description adds no value over the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: detecting large investor movements (whales) using order book and candlestick data. The phrase '簡易検出' (simple detection) and the bracket summary provide a specific verb+resource. However, it remains somewhat vague about the exact output, which could be improved.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool over sibling tools. The description implies it is for detecting whale orders, but does not provide context such as 'use when you need to identify large orders' or mention alternatives. No exclusions or best practices are included.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool detects patterns and returns context/historical stats, but does not disclose important behavioral traits such as whether it is read-only, required permissions, rate limits, or how historical statistics are computed. The description is too vague to adequately inform an AI agent about behavioral nuances.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and to the point, with a front-loaded list of patterns. It avoids unnecessary words and uses both Japanese and English for clarity. However, it could be slightly more structured, but given its brevity, it is appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (10 parameters, no output schema, low schema coverage), the description is incomplete. It does not explain the output format, how to interpret results, limitations, or prerequisites. A more detailed description is needed for an AI agent to use the tool correctly without additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With only 30% schema description coverage, the description must compensate by explaining parameters, but it does not. It mentions no parameter details beyond the tool's overall function. The schema itself provides partial descriptions for some parameters (e.g., as_of, patterns, timeframe), but the description adds no value for the remaining parameters (e.g., window_days, focus_last_n, history_horizons).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool detects candlestick patterns (doji, engulfing, hammer, harami) and provides context with historical statistics. It specifies the scope (1-3 bar patterns) and lists example patterns, making the purpose unambiguous. However, it does not differentiate from sibling tools like detect_patterns, which may have overlapping functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for detecting candle patterns but provides no explicit guidance on when to use this tool versus alternatives. It does not mention conditions, prerequisites, or exclusions. The context of sibling tools (e.g., detect_patterns) is not addressed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It implies read-only analysis of historical data, which is non-destructive. But it doesn't disclose authentication needs, rate limits, or limitations. Functional description is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences; reasonably concise. But the mixed Japanese/English could be streamlined. Front-loads the key function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no parameter explanations, and 4 parameters left undocumented. For an analysis tool with siblings, more context is needed for complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, and description does not mention any parameters (pair, topN, tolerance, lookbackDays). No guidance on what these parameters control or their default values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it auto-detects support/resistance/key levels and analyzes contact frequency/strength/breakdown. Verb+resource is specific, distinguishing it from sibling analysis tools that focus on other indicators like BB, Fibonacci, etc. However, the Japanese/English mix may slightly reduce clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like analyze_fibonacci or analyze_market_signal. The description describes function but not context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that ATR uses Wilder's method (RMA-based, period=14, matching TradingView/MT4) and mentions annualization and rolling window recommendations. However, it lacks details on destructive behavior, authorization, rate limits, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single paragraph of moderate length. It begins with a title-like bracket and covers purpose, methods, and a tip. While not verbose, it lacks clear structure (e.g., bullet points) and could be more concise by removing redundant mentions of volatility.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 9 parameters, 2 required, no output schema, and no annotations, the description is incomplete. It explains what is computed but fails to describe parameter semantics, return format, or how to interpret results, which is essential for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description provides no explanation of parameters (e.g., `pair`, `type`, `view`, `limit`, `windows`). Despite having 9 parameters with defaults and enums, the description adds no value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description begins with '[Volatility / ATR / RV]' and states it calculates volatility indicators, listing specific methods (RV, ATR, Parkinson, Garman-Klass, Rogers-Satchell). The verb '算出' (calculate) is clear, and the resource is volatility metrics. It distinguishes from sibling tools by focusing on volatility, but the technical jargon may reduce clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives. There is a tip for rolling windows ('ローリングではボラ変化を RV / Parkinson で追跡してください') but no exclusions or comparisons with sibling tools like `analyze_bb_snapshot` or `analyze_indicators`.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool returns only the latest values, which is a behavioral trait. However, it does not mention other behaviors such as read-only nature, authorization requirements, rate limits, or data source accuracy.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, consisting of two sentences and a warning note. It avoids unnecessary text, though the lack of parameter descriptions is a trade-off. The structure is acceptable for its brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of Ichimoku indicators and the absence of an output schema or parameter documentation, the description is incomplete. It does not explain how to interpret the returned values or configure the parameters for meaningful analysis, leaving gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain any of the four parameters (pair, type, limit, lookback). Users are left to infer their meanings from parameter names alone, which is insufficient for correct usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides a numerical snapshot of Ichimoku Cloud indicators, including price, cloud position, tenkan-kijun cross, and cloud slope. It distinguishes from a related sibling tool (prepare_chart_data) explicitly, but does not differentiate from other analyze_* siblings beyond the name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description notes that it provides latest values only and suggests using prepare_chart_data for time series charting. However, it does not provide guidance on when to use this tool versus other similar snapshot tools (e.g., analyze_bb_snapshot), nor does it mention prerequisites or constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must fully communicate behavioral traits. It only mentions the basic listing and ranking capability, lacking details on data freshness, rate limits, authentication, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a single sentence covering the core purpose and ranking feature. It could be slightly clearer with separate clauses, but it's efficiently front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the 4 parameters, no output schema, and sibling tools, the description is too minimal. It omits output structure, behavior of different views, and how to interpret results, making it incomplete for accurate agent usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description hints at ranking by change rate and volume, partly compensating for missing parameter details. However, it does not explain the 'view' enum or other parameters individually, leaving gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a list of all JPY pair tickers with ranking options, using a specific verb (get) and resource (all JPY pairs tickers). It distinguishes from sibling tools like get_ticker (singular) and analysis tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as get_ticker for a single pair or other analytical tools. There is no mention of appropriate contexts or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that calculations are based on recent trades (hours/limit) and lists computed metrics. However, it does not mention data source, recalc behavior, or any side effects, leaving some gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and front-loaded with core functionality in the first sentence. It uses concise phrasing, though the mix of Japanese and brackets slightly reduces clarity. No redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain return values. It hints at outputs (VWAP bands, volume distribution) but does not specify structure or format. With many sibling tools, more context on what results look like would help agent decide.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 67%. The description explains the 'hours' parameter (default 4h, max 24h) but does not detail other parameters like 'bins', 'valueAreaPct', 'tz', or 'pair'. It adds value by naming the analysis types but could better compensate for low coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it analyzes volume profile, VWAP, POC, and value area. It lists specific outputs (VWAP bands, volume per price, trade size distribution) and mentions the key parameter 'hours'. While it distinguishes from sibling tools by topic, it does not explicitly contrast with similar tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The description implies usage for volume profile analysis but does not provide context for when other tools like 'analyze_indicators' or 'get_volatility_metrics' would be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It clearly states that only latest values are provided ('最新値のみ') and points to the charting tool for historical data. It does not disclose side effects (none expected) but covers the key constraint.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively short but mixes Japanese and English, includes an emoji, and lacks clear structure. It is not overly verbose, but could be more organized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 parameters and no output schema, the description is incomplete. It mentions snapshot elements but does not define cross detection parameters or alignment states. It also omits default behaviors and error conditions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain any of the four parameters (pair, type, limit, periods). The only indirect mention is in the charting hint referencing 'SMA_25, SMA_75', but no explicit parameter semantics are provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states that the tool provides a snapshot of SMA values, cross detection (golden/dead cross), and alignment state. This clearly distinguishes it from siblings like analyze_ema_snapshot.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates that for time series chart drawing, one should use prepare_chart_data, providing a clear exclusion. However, it does not compare against other snapshot tools or suggest when to use this over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It explains that display times are formatted according to the 'tz' parameter, structured data remains in UTC ISO, and results should be rendered via 'render_chart_svg' rather than outputting SVG directly. These details provide useful behavioral context beyond a basic description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a mix of Japanese and English with multiple clauses and inline lists. While it conveys necessary information, it lacks clear structure and could be more concise. For example, the rendering instruction and timestamp formatting details could be presented more succinctly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (14 parameters, no output schema), the description provides adequate context about forming/completed detection, timezone handling, and rendering instructions. However, it does not describe the full return structure (e.g., data.patterns fields) or how the tool relates to siblings. An output schema would help, but its absence places a burden on the description to be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema coverage is only 36%, so the description should compensate. It adds some meaning for the 'patterns' parameter with recommended parameters (e.g., swingDepth, tolerancePct) and aliases. However, most other parameters (like 'pair', 'type', 'view', 'limit') are left to their schema defaults without additional explanation in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool detects chart patterns (e.g., double top, head and shoulders, triangle) and mentions it integrates forming and completed patterns. However, it does not explicitly differentiate from sibling tools like 'analyze_candle_patterns' or 'analyze_support_resistance' beyond the tool name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives. It mentions passing overlays to 'render_chart_svg' for visual confirmation, but does not explain when to choose this tool over other pattern detection or analysis tools. No when-not or exclusion criteria are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the tool returns ticker data (price, volume, 24h range), which is sufficient for a simple read operation. No mention of data freshness or limitations, but acceptable for this scope.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with a category label, front-loaded. No wasted words, but lacks parameter info.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Minimal description adequate for a simple tool with one parameter, but does not explain output structure, error behavior, or link to plural counterpart.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and description does not mention the parameter by name or explain its format, default, or allowed values. The phrase 'single pair' implies the parameter is a pair, but no concrete semantic help.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it gets ticker/price for a single pair, listing specific data fields (price, volume, 24h high/low). It distinguishes from sibling 'get_tickers_jpy' by specifying 'single pair'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use vs alternatives. The description only implies single-pair usage but does not mention when not to use or provide comparisons to analysis tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It implies a read-only operation ('get') and hints at filtering and date specification, but does not disclose pagination, rate limits, or data freshness beyond the default 60 items.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, with a clear front-loaded title and a single sentence covering core functionality. It avoids fluff but could be slightly more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 8 parameters, no output schema, and no annotations, the description is too brief. It does not explain default behavior (e.g., how 'latest' interacts with the 'limit' default of 100) or the difference between 'summary' and 'items' views.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 13% (only the 'date' parameter has a description). The description adds that filtering by amount/price is possible and mentions date specification, but does not detail the view or limit parameters, leaving significant gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb '取得' (get) and the resource '約定履歴' (transaction history), distinguishing it from sibling tools like get_candles or get_orderbook by specifying it's for transactions/trades.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions fetching the latest 60 items or by date, and filtering by amount/price, providing basic context. However, it does not explicitly state when to use this tool versus alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full burden. It discloses the snapshot-only nature and mentions zone/cross/divergence detection. However, it does not describe the output format, side effects (if any), or authentication requirements, leaving gaps in behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences and a warning, front-loading the purpose. However, the use of Japanese characters may reduce readability for non-Japanese speakers, and the structure could be slightly improved with clearer parameter hints.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 6 parameters, no output schema, and no annotations, the description is too minimal. It fails to explain what the analysis result contains, how parameters like kPeriod affect the output, or the return structure. This leaves significant gaps for an AI agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
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 mentions stochastic components (%K, %D) but does not explain the six parameters (pair, type, limit, kPeriod, smoothD, smoothK). Users must infer meaning from context, which is insufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it evaluates stochastic overbought/oversold/divergence zones and cross. It mentions 'latest status only' which differentiates it from time-series tools like prepare_chart_data. However, it could be more explicit about what specific analysis it performs compared to other analyze_* siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly warns that only latest values are provided and directs users to prepare_chart_data for time-series chart drawing. This clearly tells when not to use this tool and suggests an alternative, meeting the highest standard for usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It discloses that the tool performs server-side rendering and can accept overlays from 'detect_patterns', but does not describe output details, side effects, prerequisites, or potential errors. The behavioral profile is adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded with the core purpose. It conveys essential usage rules without unnecessary repetition, though it could benefit from clearer structuring.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's 22 parameters and no output schema, the description lacks details on return type (SVG vs. PNG), parameter interactions, and examples. It sufficiently links to sibling tools 'prepare_chart_data' and 'detect_patterns' but leaves many usage scenarios uncovered.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description mentions overlays and optional indicators as groups but adds little individual parameter meaning. With 22 parameters and only 41% schema description coverage, the description should compensate but does not, leaving many parameters under-explained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates candlestick/line charts as SVG/PNG on the server side, distinguishing it from the client-side alternative 'prepare_chart_data'. The purpose is specific and actionable, though the output format (SVG string vs. PNG file) is not explicitly clarified.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises to prioritize 'prepare_chart_data' for client-side rendering, restricts usage to explicit user requests for SVG/PNG save, and prohibits spontaneous calls. It also instructs to include indicators only when the user explicitly requests them, providing clear when-to-use and when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden. It explains the composite score uses rate of change, RSI, SMA divergence, and volume, and operates on all JPY pairs. However, it does not indicate whether the tool is read-only, real-time, or if it modifies data. The methodology disclosure is moderate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, mixing Japanese and English, and includes a bracketed tag for context. It is front-loaded with the key purpose. The single sentence is efficient but could be slightly more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description lacks details on return format (e.g., sorted list or scores). However, the parameters are well-documented. The tool's complexity (composite score) would benefit from more contextual completeness, but it is minimally adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters having descriptions. The tool description does not add meaning beyond the schema; it repeats general purpose. Baseline 3 is appropriate as the schema already documents parameter roles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as a currency strength ranking and screening tool, using a composite score for all JPY pairs. It distinguishes itself from sibling tools that focus on individual indicators (e.g., analyze_bb_snapshot, analyze_macd_cross) by offering a holistic strength assessment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states the tool is for 'finding and screening notable issues,' which implies usage for discovery, but it lacks explicit guidance on when to use this tool versus alternatives. No when-not or exclusion criteria are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description discloses a key behavioral trait: it only returns the latest values (not time series). This is useful. However, it does not explicitly state whether the tool is read-only or non-destructive, nor mention auth needs or data freshness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences, front-loading the purpose and defaults. It wastes no words. However, it could add brief parameter hints without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and 0% parameter description coverage, the description falls short. It explains one parameter (periods) and one behavioral constraint, but leaves three parameters and return format unexplained. More detail is needed for a tool with this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
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 'periods' parameter with default values, but does not describe 'pair', 'type', or 'limit'. Only one of four parameters gets meaningful context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns latest EMA values, alignment, cross, and slope with default periods 12/26/50/200. It distinguishes itself from siblings like analyze_sma_snapshot by specifying 'EMA' and from prepare_chart_data for charting.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises that for time series chart drawing, use prepare_chart_data with indicators. This provides a concrete alternative. However, it does not cover when to use this vs other snapshot tools (e.g., analyze_sma_snapshot).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so description carries full burden. It mentions parallel computation and confluence detection but lacks details on side effects, output format, or potential performance implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single focused paragraph with a clear title prefix, no redundant words, and all information front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of multi-timeframe analysis and absence of output schema or annotations, the description fails to explain what the tool returns or how to interpret confluence zones, leaving significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage, but parameter names and defaults (pair, lookbackDays with sample values) provide basic meaning. No additional explanation of array usage or constraints beyond what schema enforces.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it performs multi-timeframe Fibonacci analysis with confluence zone detection, and explicitly distinguishes from sibling analyze_fibonacci by saying 'No need to call analyze_fibonacci individually.'
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear context for when to use this tool over analyze_fibonacci (for batch analysis across multiple lookback periods), but does not mention when not to use it or specify alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Mentions SVG generation and file saving via autoSave/preferFile, but does not detail side effects, output format, or required permissions. Moderate disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise with two clear sections: purpose and usage guidelines. Mixed Japanese and English is acceptable but may reduce clarity for non-Japanese agents.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 5 parameters (including nested object), no output schema, and no annotations, the description lacks essential parameter explanations and output details. Only purpose and usage guidelines are covered.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain any parameters (pair, type, depth, autoSave, preferFile). Fails to add meaning beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it generates SVG for depth chart/order book visualization. Distinguishes from sibling prepare_depth_data by specifying it is for file saving/embedding fallback.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use this tool (fallback for SVG file saving) vs alternative (use prepare_depth_data if client-side rendering is possible), providing clear context and exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It reveals key behaviors: returns only latest values, offers two modes (default and extended), and is lightweight. However, it does not disclose potential side effects, authentication requirements, or rate limits, though such details may not be critical for a read-only snapshot tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, with each sentence adding value. It could be slightly more structured by separating parameter details, but overall it avoids redundancy and stays on point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the tool's purpose, modes, and distinguishes from a sibling for charting. However, it lacks details on output format and does not fully explain parameters. Given the absence of annotations and output schema, more context would be beneficial for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must explain parameters. It explains the 'mode' parameter with its two options but does not describe 'pair', 'type', or 'limit', leaving their semantics unclear beyond default values. This is a significant gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides a numerical snapshot of Bollinger Bands (BB, squeeze, bandwidth, zScore). It highlights being lightweight and BB-specific, distinguishing it from siblings like analyze_sma_snapshot and analyze_ema_snapshot.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly notes that latest values only are returned and directs users to prepare_chart_data for time-series charts. While it does not list when not to use this tool, it provides a clear alternative for charting needs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It does not mention whether the tool is read-only, requires authentication, has rate limits, or what side effects (e.g., no destructive actions). The description focuses on output modes but lacks transparency about the tool's operational behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise and well-structured. It begins with a clear title in brackets, then lists each mode in a bulleted format with a one-line explanation. Every sentence adds value with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there are 6 parameters, no annotations, and no output schema, the description should provide more context. It explains modes but does not clarify parameter interactions (e.g., how topN or ranges apply to each mode) or the response format. The missing details reduce completeness for a tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning for the 'mode' parameter by explaining each enum value, but the other five parameters (pair, topN, ranges, bandsPct, priceZones) are not described at all. With 0% schema description coverage, the description only partially compensates by explaining modes, leaving most parameters unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: it is an integrated tool for order book, depth, and bid-ask spread data. The multiple modes (summary, pressure, statistics, raw) are explicitly listed, distinguishing it from sibling tools like analyze_* or get_candles which focus on different data types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description describes four modes with brief explanations of what each returns (e.g., summary: top N layers+spread; pressure: buy/sell pressure per band). This provides context for when to use each mode, but it does not explicitly state when to prefer this tool over siblings or when not to use it. The guidance is implicit but adequate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must fully cover behavior. It describes core functionality (swing detection, level calculation, history) but does not explicitly confirm read-only nature or other side effects. Adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences covering purpose, functionality, and sibling recommendation. No unnecessary words, front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 5 parameters and no output schema, description is somewhat incomplete. It does not specify output format or details on reaction history. However, it provides essential functional context. Adequate but could be more comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% parameter description coverage. Description only briefly mentions swing detection and levels, but does not explain any of the five parameters (mode, pair, type, lookbackDays, historyLookbackDays), leaving the agent to infer from names. Insufficient compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description states it performs Fibonacci analysis with automatic swing detection to calculate retracement/extension levels, including historical reaction data. It distinguishes from sibling analyze_mtf_fibonacci for multi-timeframe use, making purpose specific and clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly mentions alternative sibling for multi-timeframe analysis, guiding when to use each. However, lacks other usage context or prerequisites (e.g., need for candle data).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description discloses the snapshot-only limitation and the composite nature. No mention of side effects, but it's a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with key info upfront and bullets, but bilingual text (Japanese/English) adds some verbosity. Clear and focused overall.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and 5 undocumented parameters, description fails to explain parameters or return format. Incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, and description provides no information about the 5 parameters (pair, type, windows, bucketMs, flowLimit). Agent cannot infer their meaning from the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it evaluates market signal as a single composite score from 5 factors (-100 to +100). It distinguishes from siblings like prepare_chart_data for charts and lists other detailed analysis tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says it's best for starting point/screening, warns that it's only a snapshot and not for time series (use prepare_chart_data), and references other tools for detailed analysis.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description discloses important behavioral details: internal sorting by timestampMs ascending, deduplication logic using timestampMs:price:amount:side when merging data sources, and the fact that hours parameter can fetch across multiple days. This adds substantial value beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two clear sections: purpose/usage and processing contract. It front-loads the main function and uses efficient language, though the Japanese '加工契約' section is somewhat technical but necessary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should clarify return structure. It mentions view parameter options (summary, compact, buckets, full) but does not explain what each returns. The tool has 8 optional parameters with defaults, but no description of default behavior beyond hours/limit priority.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 63%, and the description adds meaning for key parameters: explains that hours is prioritized over limit, specifies that limit refers to execution count not bucket count, and clarifies that hours automatically spans multiple days. This helps agents understand parameter interplay.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: analyzing fund flow metrics (flow/CVD/aggressor ratio/buy-sell pressure) from execution data. It specifies detection of CVD, aggressor ratio, and spikes, and distinguishes it from sibling analysis tools by focusing on flow-specific metrics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description recommends using 'hours' over 'limit' for time range specification, but does not provide explicit guidance on when to use this tool versus alternatives. There is no 'when-not-to-use' or mention of prerequisites, limiting clarity on appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavioral traits: it detects gaps, duplicates, OHLCV consistency, price/volume outliers, computes a 0-100 quality score (A-F), auto-detects liquidity tiers, and adjusts thresholds. It does not mention side effects or rate limits, but the core behavior is well covered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a dense paragraph with relevant information, structured from purpose to details to usage. Every sentence adds value, and it is front-loaded with the tool's role. It is concise given the complexity, though could be slightly streamlined.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers purpose, checks, score, tier detection, and adjustability. However, with no output schema, it lacks explicit details on the return structure or format of the quality score. This is a notable gap for a validation tool with multiple output components.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 71% (5/7 parameters described). The description adds context about auto-detected tiers and adjustable thresholds, but does not provide additional per-parameter details beyond the schema. Baseline is 3, and the description does not significantly enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'OHLCVローソク足データの品質検証' (OHLCV candlestick data quality validation), lists specific checks (completeness, duplicates, consistency, outliers), and distinguishes from sibling analysis/retrieval tools. It uses a specific verb and resource, fulfilling the highest clarity criterion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says to use this tool before analysis or backtesting to verify data reliability ('分析やバックテスト前に「このデータ信用できる？」を確認するためのツール'). While it doesn't explicitly exclude alternatives or name them, it provides clear contextual guidance for when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so description carries full burden. It details return format, bid/ask ordering, band calculation, and JPY rounding. Lacks auth/rate limit info but sufficient for behavioral understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with purpose, each sentence adds value. Slightly long but well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Thorough description of return data, ordering, and band calculation. No output schema, but covers essential details. Could mention error handling.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 67%. Description adds context for bandPct (mid ± range) and explains levels default, but pair lacks description. Adds some value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Explicitly states it is the first-choice tool for depth chart visualization, calls getDepth API, and returns cumulative volume array. Clearly distinguishes from render_depth_svg.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
States when to use (visualizer capable) and when to use alternative render_depth_svg (file saving). But does not mention other alternatives like get_orderbook.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool is for visualization, takes candle data and pattern info, and outputs an SVG to be rendered via a widget. It also prohibits direct SVG output. However, it does not explicitly state read-only nature or authentication needs, though these are implied.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is moderately concise, mixing Japanese and English. It front-loads the purpose with brackets but could be more structured. Some redundancy exists (e.g., repeating 'education'). It is not overly long but has room for improvement.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description ties the tool to analyze_candle_patterns and provides usage constraints. However, it lacks explanation of the output format (SVG URL or string), error scenarios, and limitations like max candles (though schema defines max 10). Overall, it is fairly complete but leaves some ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is high (75%), so baseline is 3. The description adds minimal semantic value beyond linking to analyze_candle_patterns. It does not detail parameter meanings or constraints beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is for educational candle pattern diagrams, specifically visualizing results of analyze_candle_patterns for beginners. The verb 'レンダリング' (render) and the resource 'candle pattern diagram' are explicit, distinguishing it from sibling tools like render_chart_svg and render_depth_svg.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use: only when user explicitly says 'show me a diagram' etc., and prohibits spontaneous calls. It also details output handling: pass data.svg to Visualizer widget code, and prohibits direct SVG output to chat. This provides clear context for invocation and processing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full transparency burden. It discloses the dual-mode behavior, screening parameters (crossType, limit, sortBy, etc.), and deep analysis features (forming detection, stats). It does not mention destructive actions, auth, or rate limits, but as a read-only analysis tool this is acceptable. Score 4.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, using bullet points for screening parameters. It is front-loaded with purpose and mode distinction. The mixed Japanese/English might reduce clarity for some agents, but overall it is structured efficiently. Score 4.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description does not explain return values (e.g., what fields are in the results). It mentions '上位N件' but lacks detail on output structure. Additionally, error conditions or edge cases are not covered. For a complex tool with nested objects, this is a gap. Score 3.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 55%, and the description adds value by explaining the role of parameters in context (e.g., crossType for screening, pair for mode selection). It does not fully compensate for all 11 parameters but provides meaningful semantic grouping (screen parameters). Score 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool detects MACD crosses (golden/dead cross) and distinguishes two modes: screening multiple pairs (when pair is omitted) and deep single-pair analysis with forming detection and historical stats. This specificity and differentiation from sibling tools like analyze_ema_snapshot justify a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use each mode: 'pair省略: 複数銘柄スクリーニング' and 'pair指定: 単一ペア深掘り分析'. While it doesn't list alternatives or when not to use, the context is clear enough for an agent to decide. Score 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the burden. It states the tool returns text analysis, implying it is a read-only query with no destructive side effects. While it does not explicitly say 'no modifications', the nature of analysis is clear and there is no contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with an additional line for sibling references. It is front-loaded with the tool's purpose and key indicators. No superfluous text, but could be slightly more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description adequately covers the tool's purpose, usage hint (limit), and alternatives. It lacks details on return format beyond 'text' and does not explain all parameters fully, but is sufficient for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, so the description must compensate. It gives meaningful guidance for the 'limit' parameter (specify sufficient value like 200), but does not explain 'pair' or 'type' parameters. Partial compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states it performs comprehensive analysis of technical indicators (RSI, MACD, SMA) and returns latest values, trend judgments, and signals as text. It also distinguishes itself from sibling tools by mentioning that drawing charts and backtesting are handled by other tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description advises specifying a sufficient limit (e.g., 200 daily candles) and clearly directs when to use alternative tools: for drawing charts use prepare_chart_data/render_chart_svg, for backtesting use run_backtest. This provides explicit when-not and alternative usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses key behavioral traits: how date and limit interact (returning candles before the end of the specified day in the given timezone), timezone handling with fallback to Asia/Tokyo, and dynamic maximum limits based on the candle type. This is thorough and transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: a single paragraph covering the core functionality, followed by an important note about backtesting. Every sentence provides value, with no redundancy. It front-loads the purpose and references the schema for details, making it efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers core functionality, parameter usage, timezone handling, and differentiation from backtesting. However, it lacks information about the output format (no output schema exists) and does not mention error conditions or authentication. For a data retrieval tool with 6 parameters and no output schema, this is a noticeable gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only tz, date, limit have descriptions in the schema). The description text adds some high-level context about date interpretation and backtesting but does not significantly enhance understanding of the undocumented parameters (pair, type, view). The baseline for 50% coverage is 3, and the description does not sufficiently compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves OHLCV/candle data for various timeframes, using the verb '取得' and specifying the resource 'ローソク足'. It distinguishes itself from sibling tools like run_backtest by noting that backtesting should use that tool instead. The purpose is specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises using run_backtest for backtesting instead of get_candles, providing a clear when-not-to-use case. It also explains date interpretation and limit behavior. However, it does not mention alternatives among sibling data retrieval tools like get_ticker or get_orderbook, leaving some gaps in guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are given, so the description must carry the burden. It discloses the process: data fetch, calculation, chart drawing, and includes details on SVG charts, equity curve JSON, and chartDetail behavior. It does not mention permissions or rate limits but covers core behavior well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with bullet points and sections, front-loading the purpose. It is slightly long but every sentence adds value, especially for a complex tool with 12 parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and lack of output schema, the description covers most important aspects: strategies, periods, timeframes, output format (SVG, equity curve JSON). Missing are explicit return value structure beyond the JSON mention and potential error cases, but it is largely complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds significant value: explains dynamic fee_bp resolution, start_date/end_date override, chartDetail sampling, savePng vs includeSvg, and strategy parameter overrides. This goes well beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states '汎用バックテスト' (generic backtest) and lists specific strategies, periods, and timeframes. It distinguishes itself from sibling analysis tools by focusing on end-to-end backtesting.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use the tool (for backtesting strategies) and details on parameter usage, but does not explicitly state when not to use or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full disclosure burden. It reveals that the default return is only OHLCV, describes the response format, notes that JPY pair prices are rounded to integers, and explains tz behavior for local time conversion. However, it does not explicitly state that the tool is read-only or destructive, though the context implies read-only. A mention of authorization or rate limits would elevate it further.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively long but well-structured, with a clear title line, bullet-point warnings, and separate notes on response format and tz. It front-loads the purpose and critical usage constraints. Minor redundancy: 'デフォルトはローソク足（OHLCV）のみ返す。indicators 未指定 = ローソク足のみ。' repeats the same message. Overall, each sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (5 parameters, no output schema, many sibling tools), the description is quite complete. It explains the response format, default behavior, and tz effect, and references sibling tools for related tasks. However, pair and type parameters are not explained (only defaults in schema), and the absence of an output schema means the agent relies entirely on the description for return understanding. Still, the provided information is sufficient for most use cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 20%, so the description must compensate. It does so effectively for tz (explains local time and labels), limit (warns about default and when to increase), and indicators (lists allowed values and emphasizes explicit specification). However, pair and type receive minimal elaboration beyond defaults. The description adds significant meaning beyond the schema for three of five parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as the first-choice for chart drawing (candlestick/visualization). It specifies that it returns OHLCV data with optional indicators and distinguishes from sibling tools like render_chart_svg and analyze_indicators. The verb 'prepare_chart_data' is specific and the resource is well-defined.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool (first choice for charting) and when not (e.g., for SVG/PNG files use render_chart_svg; for indicator analysis use analyze_indicators). It includes critical warnings: default limit 30, only increase if user specifies a period; only specify indicators if user explicitly requests; and caution about context consumption. This fully addresses usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description fully covers behavioral traits: it explains that it forces a cache refresh, mentions the default TTL (1h), and clarifies that all pairs are re-acquired even if a specific pair is given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with category and endpoint, and every sentence adds value. No waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one optional parameter and no output schema. The description fully explains the tool's purpose, usage, and parameter behavior, making it complete for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds critical clarity: it explains that the 'pair' parameter only highlights that pair's rate and does not limit re-acquisition to that pair. This goes beyond the schema description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool forces re-acquisition of TTL cache for fee rates, with specific context (maintenance/fees) and a concrete use case (campaign boundaries). It is distinct from sibling tools, which are all analysis-oriented.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly mentions when to use (to refresh fee rate cache, e.g., at campaign boundaries). It does not explicitly state when not to use, but the context implies it is not for normal operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![bitbank-lab-mcp MCP server](https://glama.ai/mcp/servers/tjackiet/bitbank-lab-mcp/badges/card.svg)](https://glama.ai/mcp/servers/tjackiet/bitbank-lab-mcp)

Score Badge

Copy to your README.md:

[![bitbank-lab-mcp MCP server](https://glama.ai/mcp/servers/tjackiet/bitbank-lab-mcp/badges/score.svg)](https://glama.ai/mcp/servers/tjackiet/bitbank-lab-mcp)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tjackiet/bitbank-lab-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server