Server Quality Checklist

Tool Scores

• tool_get_portfolio_backtest_resultsB
  3.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly indicates this is a retrieval operation for completed backtests and adds a sharing protocol for the results URL. It does not describe error behavior for incomplete/failed backtests, authentication needs, or rate limits, so transparency 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 compact, front-loaded with the core purpose, and uses a bulleted list for return types. The IMPORTANT instruction is actionable and not wasted. The return list may somewhat duplicate output-schema details, but it does not make the description overly long.

  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 one-parameter retrieval tool with an output schema, the description covers the completion precondition and the required sharing behavior. It is missing guidance on how to obtain a valid portfolio_backtest_id and what happens when the backtest is still pending or failed, which would be useful in a sibling-tool 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?

  The schema has 0% parameter description coverage and the one parameter, portfolio_backtest_id, is only minimally explained by the phrase 'completed portfolio backtest'. The description does not say where to obtain the ID, what format it should be in, or how the ID relates to other portfolio-backtest tools.

  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 states a specific verb ('Get') and resource ('results of a completed portfolio backtest'), and lists the returned data categories. It does not explicitly distinguish itself from sibling tool_get_backtest_results, but the 'portfolio' qualifier and the URL emphasis make its scope reasonably clear.

  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 word 'completed' tells the agent this tool should be used only after a backtest has finished, and the IMPORTANT note provides a clear post-call instruction to share results_url. However, it does not explicitly mention alternatives like tool_get_portfolio_backtest_status for checking progress or tool_get_backtest_results for non-portfolio backtests.

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

• tool_get_optimization_statusB
  3.3/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral disclosure burden. It clearly indicates this is a read-only status check and lists what is returned, but it does not disclose behavior for invalid IDs, completed optimizations, or polling expectations.

  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 fluff. The verb and resource are front-loaded, and the second sentence efficiently lists the return fields.

  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 is simple with one parameter and has an output schema, so the return fields do not need extensive explanation. However, with no annotations, the description is missing useful context about when a status check is appropriate and how this relates to fetching final optimization results.

  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 should compensate. The single parameter optimization_id is evident from the schema and name, and the description references 'a running optimization,' but it never explicitly defines optimization_id or explains where to obtain it.

  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 states a specific action ('Check the status') and a specific resource ('a running optimization'), and lists the returned data fields. It is distinguishable from siblings like get_optimization_results and get_backtest_status, though it does not explicitly call out the distinction.

  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 gives no guidance on when to use this tool versus alternatives. It does not mention that this is only for optimizations, not backtests, or that results should be retrieved separately via get_optimization_results.

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

• tool_get_portfolio_backtest_statusB
  3.3/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the disclosure burden. It usefully reveals the possible status values and progress percentage, which helps set expectations. However, it does not explicitly state that this operation has no side effects, nor does it describe error behavior for invalid or unknown portfolio_backtest_id values.

  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 compact and well-structured: the first sentence states the action, and the second sentence summarizes the return information. There is no filler or repetition, and it is appropriately sized for a simple status-check tool.

  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 one-parameter status tool with an output schema, the description covers the core purpose and return behavior. However, it leaves usage context and parameter provenance to inference, and it does not clarify its relationship to the similar sibling tool_get_backtest_status. These gaps make it minimally adequate rather than fully complete.

  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 does not mention portfolio_backtest_id at all. The parameter's name makes its purpose somewhat obvious, but the description does not explain where the ID comes from, its format, or that it should be the ID returned by tool_run_portfolio_backtest.

  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 uses a specific verb ('Check') and resource ('status of a portfolio backtest') and explicitly lists the returned statuses and progress percentage. It clearly communicates the tool's function, though it does not differentiate itself from the sibling tool_get_backtest_status beyond the word 'portfolio', and 'running' is slightly ambiguous since 'completed' is also a possible status.

  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 this tool is used to poll or inspect an ongoing portfolio backtest by returning statuses like 'queued' and 'running'. However, it provides no explicit guidance on when to use this tool versus alternatives such as tool_get_backtest_status or tool_get_portfolio_backtest_results, and it does not state that it should be called after tool_run_portfolio_backtest.

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

• tool_get_optimization_resultsA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description carries the full behavioral burden. It transparently frames the tool as a read operation and lists the shape of the returned data, but it does not disclose what happens if the optimization_id is missing, invalid, or belongs to an optimization that has not completed. There is also no explicit statement that the call has no 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and front-loaded with the core action, followed by a concise list of return fields. Every element adds useful orientation without excessive detail.

  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?

  This is a simple one-parameter retrieval tool, and the description covers the main precondition ('completed') and the outcome. The presence of an output schema reduces the need to duplicate return details, though a brief pointer to tool_get_optimization_status for in-progress optimizations would make it fully 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 provides no description for optimization_id, and the tool description does not explicitly explain that this parameter is the identifier returned when an optimization is submitted. However, the phrase 'results of a completed optimization' plus the parameter name make the intended meaning reasonably clear.

  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 uses a specific verb-resource pair ('Get the results') and clearly scopes the tool to completed optimizations, distinguishing it at a glance from status or backtest tools. However, it does not explicitly name a sibling tool or state what this tool is not, so it stops short of full differentiation.

  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 qualifier 'completed' implies the tool should only be called after an optimization finishes, and the sibling tool_get_optimization_status is the natural alternative for ongoing runs. But the description does not explicitly say when to use this tool instead of status or any other sibling, so the guidance is only implied.

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

• tool_get_backtest_resultsA
  3.8/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does well: it lists the return fields, notes that trades_preview is limited to the first 10 trades, and adds an actionable requirement to share results_url. It omits failure modes or prerequisites beyond 'completed,' but for a simple retrieval tool this is strong coverage.

  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 compact and well-structured: a one-line purpose, a bulleted return summary, and a prominent IMPORTANT note. Every sentence contributes meaningful information, and the mandatory sharing behavior is front-loaded at the end where it still stands out.

  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?

  For a single-parameter getter with an output schema, the description covers the essential purpose, return contents, and required follow-up behavior. It could be more complete by explaining what happens if the backtest_id is invalid or the backtest is not yet complete, but those are minor gaps for a tool this simple.

  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 input schema has only backtest_id with zero schema description coverage, and the tool description does not elaborate on the parameter beyond the obvious name. Since backtest_id is self-explanatory and has no enum or complex constraints, the lack of added detail is not a major issue, but the description also does not compensate for the missing schema docs.

  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 uses a specific verb and resource: 'Get the results of a completed backtest.' It clearly identifies a read operation and distinguishes it from running or status tools. However, it does not explicitly differentiate itself from sibling tools like get_backtest_status or get_portfolio_backtest_results.

  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 word 'completed' implies this tool should be used only after a backtest finishes, which is useful contextual guidance. However, it does not explicitly state when not to use it or mention alternatives such as get_backtest_status for polling progress. The instruction to always share results_url is a clear usage note but not a selection guideline.

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

• tool_list_backtestsA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the behavioral disclosure burden. It does indicate that this is a read-only listing operation ('List'), scopes to 'your previous' backtests, and clarifies the output is 'summary info.' However, it does not disclose ordering, whether running/queued backtests are included, or any filtering behavior beyond what the schema implies.

  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 appropriately short and front-loaded. The first sentence states exactly what the tool does; the second provides actionable context. There is no redundant or filler content.

  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 simple listing tool with an output schema, the description gives adequate high-level context. However, with no schema descriptions and no annotation coverage, the optional limit and symbol filters are not explained, and no guidance directs the agent to related result/status tools. The description is minimally sufficient but has clear gaps.

  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 needs to compensate by explaining limit and symbol. It does not mention either parameter, leaving the agent to infer meaning solely from parameter names and defaults. The parameter names are self-explanatory but the description adds no semantic value about them.

  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 a specific action ('List') and a specific resource ('your previous backtests') with the type of output ('summary info'). This distinguishes it from sibling tools like tool_get_backtest_results, which would provide full results, and tool_list_optimizations, which covers a different resource.

  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 a clear use case: 'review past experiments and compare strategies.' It does not explicitly mention when not to use this tool or point to alternatives such as tool_get_backtest_results for detailed output, so it stops short of full exclusion guidance.

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

• tool_run_portfolio_backtestA
  3.8/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does a good job: it discloses the async pattern, explains that a portfolio_backtest_id is returned, and instructs polling for status then fetching results. It also clarifies that the same strategy is applied across all assets. Minor omissions like validation of weight sums or side effects are not disclosed, but the key behavior is covered.

  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 well-structured and appropriately sized: an opening sentence, a short explanation, a bulleted asset spec, a concrete example, and the follow-up workflow. It is front-loaded and every section contributes useful information without filler.

  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?

  Despite strong asset documentation and a clear workflow, the description is not complete enough for a complex 7-parameter tool with nested objects and no annotations. The required strategy object is undocumented, date/timeframe formats are missing, and optional parameter semantics are not explained. An agent cannot confidently construct a full valid request without additional context.

  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 meaningfully documents the assets parameter with symbol, weight, the sum-to-1.0 constraint, and an example. However, the strategy parameter is essential but left completely opaque, and timeframe, start_date, end_date, commission, and initial_cash receive no explanatory attention.

  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 a specific verb and resource: running a portfolio backtest across multiple assets with weighted allocation. It clearly distinguishes itself from single-asset backtest siblings by emphasizing multiple assets, weights, and the same strategy applied to all assets.

  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 gives clear context for the multi-asset portfolio use case and the follow-up workflow (poll status, fetch results). However, it never explicitly contrasts this with tool_run_backtest or states when to choose one over the other, so the usage guidance is implied rather than explicit.

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

• tool_list_optimizationsA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral disclosure burden. It conveys that the tool is a read-only listing operation and that results include best parameters, but it does not describe ordering, pagination, or how the limit and symbol parameters affect output. For a simple list tool this is adequate but not rich.

  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 sentences with no wasted words. The primary purpose is front-loaded, and the follow-up usage note earns its place by adding context for when to invoke the tool.

  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 low complexity (two optional parameters with defaults) and the presence of an output schema, the description covers the core purpose and usage adequately. The main gap is the unstated meaning of the 'symbol' parameter, but this is a minor omission for a listing tool.

  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 does not explain either 'limit' or 'symbol'. The description adds no meaning beyond the raw schema, so an agent must infer the purpose of these parameters from their names and defaults, which is insufficient.

  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 a specific verb ('List') and resource ('your previous optimizations / parameter sweeps'), making the tool's purpose unambiguous. It clearly differentiates from sibling tools like tool_list_backtests and tool_get_optimization_results by focusing on listing past optimization runs.

  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 second sentence 'Use this to review past optimization runs and their best parameters' provides a clear usage context. It does not explicitly mention alternatives or exclusions, but the sibling tool names make the distinction between listing optimizations vs. backtests or fetching detailed results reasonably clear.

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

• tool_get_backtest_statusA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden. It discloses the operation type (checking status, not modifying anything) and the exact return values: status enumeration values and progress percentage. It could add polling behavior semantics, but for a simple status tool this is adequately 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?

  Two sentences with no filler: the purpose is front-loaded, and the return contract is stated briefly. Every sentence adds value.

  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?

  For a low-complexity tool with a single parameter and an output schema, the description is reasonably complete. It explains what the tool does and what the caller receives. It lacks explicit guidance about sourcing backtest_id and polling expectations, but these are minor given the simple schema and output schema presence.

  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 adds only indirect meaning: backtest_id is the identifier of the backtest whose status is checked. This is minimally sufficient for a single self-descriptive parameter, but it does not state where the ID comes from or provide format/example guidance.

  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 a specific verb and resource: 'Check the status of a running backtest' and explicitly lists the expected return values. It clearly distinguishes this from sibling results tools and from optimization/portfolio backtest status tools by naming 'backtest' as the focus.

  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 after a backtest has been started and before retrieving results, but it does not explicitly say when to use this tool versus tool_get_optimization_status or tool_get_portfolio_backtest_status. There is no clear exclusion or alternative routing guidance.

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

• tool_get_price_dataA
  4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the behavioral burden. It discloses an important limitation: returns 'summary statistics and a preview of the data (not the full dataset).' It also enumerates valid timeframes. It does not mention rate limits, date format requirements, or data source quirks, but the primary behavioral caveat is clearly stated.

  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 compact and front-loaded with the core action. Every sentence earns its place: what it fetches, what it returns, when to use it, and valid timeframes. There is no filler or redundant restatement of the tool name.

  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 is adequate for orienting an agent and mentions the key preview limitation, and an output schema exists to describe returned data. However, it omits practical details needed to call the tool correctly, such as accepted date formats for start_date/end_date and any constraints on symbol or historical data availability.

  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 for all four parameters. It adds value only for the timeframe parameter by listing valid values. The symbol, start_date, and end_date semantics — especially date formatting and whether end_date is inclusive — are left undocumented.

  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 a specific verb and resource: 'Fetch historical OHLCV price data for an asset.' It also distinguishes itself from sibling tools by framing this as pre-backtest price examination (e.g., tool_run_backtest, tool_optimize_strategy). The supported timeframes further reinforce the tool's specific scope.

  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 states when to use the tool: 'Use this to examine price history before defining a backtest strategy.' This gives clear context for selecting this tool over backtest and optimization siblings, though it does not explicitly say when not to use it or name alternative tools.

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

• tool_list_available_assetsA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full behavioral burden. It accurately conveys a read-only listing operation with filtering, but does not mention pagination, sorting, response shape, or any limits. This is adequate for a simple listing tool but not richly 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?

  Two short sentences with no filler. The main purpose is front-loaded and the filter description is concise and directly actionable.

  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?

  For a simple list tool with two optional parameters and an output schema, the description covers the essential purpose and parameter semantics. Minor gaps like exact asset_type enum values and response ordering are not critical given the output schema exists.

  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 0%, so the description must compensate for the bare parameter names. It does: 'asset_type' is explained with example values (crypto, forex, commodity) and 'search' is explained as searching by symbol or name.

  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 a specific verb ('List') and resource ('tradeable assets available for backtesting'), and the filter intent is explicit. This distinguishes it from sibling tools that run backtests, optimize strategies, or retrieve results.

  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: this tool lists assets available for backtesting, implying it should be used when discovering which symbols or asset types are supported. It does not explicitly mention alternatives or exclusions, but the purpose is distinct enough from siblings.

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

• tool_run_backtestA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral disclosure burden. It transparently reveals the asynchronous execution model: the tool returns only a backtest_id and requires polling. It also explains direction-specific rule semantics, which is important behavioral context beyond the bare schema.

  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 well-organized with bullets, clear sections, and meaningful examples such as '0.05 = 5%'. Every sentence contributes useful information, and the structure makes a complex nested input digestible without unnecessary fluff.

  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?

  For a complex tool with nested objects and an asynchronous workflow, the description covers strategy construction, direction variants, rule definitions, and the follow-up polling sequence. It leaves some gaps around scalar parameter formats and potential error cases, but it is broadly complete enough for an agent to invoke the tool correctly.

  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 does thoroughly for the strategy object, detailing all subfields and rule syntax. However, top-level parameters like symbol, timeframe, start_date, end_date, commission, и initial_cash are left unexplained, forcing the agent to infer format and meaning.

  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 opens with a specific action ('Define and execute a trading strategy backtest') and identifies the tool's place in the workflow by stating it returns a backtest_id that is later used with status and result tools. This clearly distinguishes it from siblings like get_backtest_status and get_backtest_results.

  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?

  It provides explicit follow-up guidance: poll with get_backtest_status, then retrieve results with get_backtest_results. It does not explicitly contrast against optimize_strategy or portfolio backtest tools, but the described workflow makes the primary use case unambiguous.

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

• tool_optimize_strategyA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the behavioral burden. It discloses that the tool is asynchronous by returning an optimization_id and requiring polling via get_optimization_status. It also specifies ranking behavior and optional constraints, which helps the agent anticipate the operation's scope.

  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 well-organized: a one-line purpose, then concise parameter documentation with bullets and an example, then the asynchronous workflow. Every sentence contributes necessary information, and the structure makes it easy for an agent 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?

  The description covers the essential workflow, key parameter shapes, and the ranking metric options. It is somewhat incomplete on the structure of the strategy object and the expected date format, but the presence of an output schema and the clear async flow keep this from being a significant gap.

  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 0%, so the description must compensate. It does so well for the most complex parameters, explaining param_ranges structure, constraint format with an example, and rank_by options. It does not document every remaining parameter such as strategy, date formats, commission, or initial_cash, but those are more self-explanatory from their names.

  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 opens with a clear verb and object: 'Run a strategy optimization / parameter sweep.' It further clarifies by saying it tests multiple parameter combinations and ranks by a metric, which distinguishes it from the backtest siblings. The follow-up pointer to status/results tools completes the purpose picture.

  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 makes the tool's role clear as a parameter-sweep operation, implicitly differentiating it from single-run backtests. It explicitly names the follow-up tools get_optimization_status and get_optimization_results, giving the agent a full workflow. It stops short of listing explicit when-not conditions or comparing against run_backtest, so it does not earn a 5.

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