Server Quality Checklist

Tool Scores

• analyzeA
  3.9/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations exist, so the description carries full burden. It discloses that it fetches candles locally and sends only numeric data to the API, and that it requires a TRADE_ANALYTICS_API_KEY. This provides good transparency, though error cases or side effects are not mentioned.

  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 with no redundant information. It front-loads the purpose and mentions key outputs and prerequisites concisely.

  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 lack of annotations and output schema, the description covers the core purpose and some parameter hints but fails to explain several parameters (session, timezone, timeframe, max_candles) clearly. Overall adequate but with 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 description coverage is 0%, so the description must compensate. It explains the trades array structure and the stop parameter for R-multiples, and mentions point_value for P&L. However, other parameters like session, timezone, timeframe, and max_candles are not explained.

  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 analyzes trades and lists specific metrics (MAE/MFE, R-multiple, etc.), distinguishing it from sibling tools like resolve_symbol or render.

  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 it is PAID and needs an API key, and gives hints on input structure (add stop for R-multiples). However, it lacks explicit guidance on when to use this tool versus alternatives.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• resolve_symbolA
  4/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries full burden. It states the tool runs locally, is free, and requires a Databento key, which provides essential behavioral context. It does not mention side effects (likely none), rate limits, or caching, but the disclosure is adequate for a read-only resolution tool.

  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 three sentences, front-loading the core purpose with examples in the first sentence. The subsequent two short sentences add behavioral context without waste. Very efficient and easy to parse.

  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 simplicity (2 params, no output schema), the description covers inputs implicitly, outputs (lists fields), and behavioral context (local, free, key). A minor gap is the lack of explicit date parameter documentation, but overall it is reasonably 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?

  Schema description coverage is 0%, so the description must explain both parameters. It clearly explains 'query' with examples ('MNQ', 'micro nasdaq'), but the 'date' parameter is only indirectly referenced via 'front-month' and lacks explicit explanation of its purpose or format. This leaves a 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 uses the specific verb 'Resolve' and resource 'symbol', providing concrete examples ('MNQ', 'micro nasdaq') and listing the output fields (root, continuous symbol, etc.). It clearly differentiates from sibling tools like get_price_context, render, and analyze, which have different purposes.

  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 implies usage when a user mentions a symbol needing resolution, but it does not explicitly state when not to use the tool or how it compares to alternatives like get_price_context. Sibling tools are not addressed, leaving room for ambiguity.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• renderA
  4.2/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description fully discloses behavioral traits: it is a paid feature, fetches data locally but sends a numeric slice to the API, returns a PNG and saves it to a file, and mentions the saved path in the text result. This goes beyond what the structured fields offer and provides transparency about side effects and authentication.

  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 a single, focused paragraph of four sentences. Each sentence adds value: purpose, cost/auth, data handling, output, and usage tips. It is front-loaded with the main action and avoids redundancy. Every sentence earns its place.

  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 complexity (15 parameters, nested objects, no output schema), the description provides a high-level overview but misses details. It explains the main output and file-saving but does not cover `risk`, `markers`, `style`, `session`, `timezone`, or other schema properties. The return format is partially described, but the 'text result' for the path is vague. Additional details would be needed for full completeness.

  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% and the description only mentions three parameters (`save_path`, `format`, `include_base64`) in passing. The other 12 parameters (e.g., `symbol`, `start`, `timeframe`, `style`) are not explained. The description does not compensate for the lack of schema documentation, leaving agents with incomplete guidance for parameter usage.

  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 'Render a candlestick chart image of a trade' with a specific verb and resource. It distinguishes itself from sibling tools (resolve_symbol, get_price_context, analyze) by focusing on chart rendering. Additional details about output format and saving file reinforce the purpose.

  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 mentions a prerequisite ('needs TRADE_ANALYTICS_API_KEY') and gives usage tips like using `save_path`, `format:'svg'`, and `include_base64:true`. It implicitly suggests when to use (for charting) but does not explicitly state when not to use or compare to siblings. The context is clear but exclusions are absent.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• get_price_contextA
  4.3/5.0
  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 free, local fetch, and JSON return. It mentions auto-derivation of window from markers with span padded (~60 candles). Could mention rate limits or error handling, but overall sufficient for a read-like operation.

  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?

  Two concise sentences: first states core function, second provides usage guidance and sibling differentiation. No wasted 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?

  The tool has 14 parameters, nested objects, and no output schema. The description provides some context (auto-derivation, sibling links) but omits details for many parameters and does not describe the return structure beyond 'JSON'.

  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% and there are 14 parameters. The description adds meaning for markers, risk, timeframe, start, end, and link to render/analyze tools. However, many other parameters (levels, session, timezone, indicators, max_candles, etc.) are left unexplained, requiring the agent to infer from 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 the tool returns OHLCV candles and trade markers as JSON for a symbol/window, using a local Databento key. It distinguishes from siblings by directing to render/analyze tools for chart images or trade analysis.

  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 tells when to use this tool vs alternatives: 'For a chart image or trade analysis, use the render / analyze tools.' Also provides guidance on how to omit timeframe/start/end to auto-derive the window from markers, and how to pass fills and risk.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.