Server Quality Checklist

Tool Scores

• run_backtestB
  3.2/5.0
  Behavior3/5

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

  With no annotations, the description carries the disclosure burden and does add useful behavioral context: it consumes a quota, demands confirm=true, and must not be used for live trading. Yet it omits other effects such as whether the operation is destructive, how long it runs, or what happens if confirm is false.

  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 tightly written sentences with no filler. The most critical information — the confirm requirement and quota consumption — appears first, and the live-trading warning is a clear, extra safety boundary.

  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?

  For an 11-parameter tool with no output schema and no annotations, this description is too thin. It covers the invocation guardrail but omits practical details like date format expectations, parameter relationships, what results are returned, and how this differs from preview_backtest.

  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, but it only addresses the confirm parameter. It gives no meaning for startDate, endDate, lots, expiry, target, stopLoss, entryTime, exitTime, or underlying, leaving the agent to infer everything from raw schema constraints.

  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 identifies a specific verb ('Configure and run'), a distinct resource ('AlgoTest Backtester'), and notes it is not for live trading. However, it does not differentiate from sibling tools like backtest_strategy or preview_backtest, so it is clear but not fully distinctive.

  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?

  It gives an explicit prerequisite ('Requires confirm=true') and a rationale ('consumes a backtest quota'), plus an exclusion ('Never use for live trading'). It does not say when to prefer this tool over preview_backtest or backtest_strategy, leaving relative usage context implicit.

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

• preview_backtestB
  3.4/5.0
  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. It usefully discloses that the tool does not start a backtest and operates in the 'local browser profile.' Yet it does not explain side effects, persistence, browser session state, or whether existing configuration is overwritten.

  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 primary action. Every clause adds context, and 'Use this first' is a useful directive. However, for a tool with this many parameters, the brevity edges toward underspecification.

  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?

  The tool has 10 parameters, no annotations, no output schema, and sibling tools for execution and results. The description covers only the highest-level purpose and ordering; it lacks parameter guidance, side-effect detail, and a clear relationship to the other backtest tools.

  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 input schema has 10 parameters with 0% description coverage, and the description names none of them. Without any explanation of startDate, endDate, stopLoss, target, or the enum fields, an agent has no semantic guidance 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?

  The description uses a specific verb and resource: 'Configure AlgoTest Backtester in the local browser profile.' It also differentiates from the sibling run_backtest by explicitly stating it does so 'without starting a backtest,' and 'Use this first' establishes its role as a precursor in the workflow.

  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?

  'Use this first' gives an explicit when-to-use instruction and implies this precedes backtest execution. However, it does not name sibling alternatives like backtest_strategy or run_backtest, nor does it state when this tool should NOT be used.

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

• backtest_strategyA
  3.6/5.0
  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 burden. It explicitly discloses that the tool never performs live trading and explains the preview-versus-run conditional based on confirm. This adds meaningful safety and control information, though it does not cover side effects like result persistence or browser interaction hinted at by close_browser.

  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 main action and conditional behavior are front-loaded, and the critical safety note ('Never performs live trading') is isolated at the end. Every word 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?

  The description covers the core invoke condition and safety, but with no output schema it omits what a 'preview' looks like, whether results are returned directly or need to be fetched via get_results, and how this tool relates to the sibling run/preview tools. An agent can call it correctly but may not know the follow-up steps.

  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 0%, so the description must compensate. It does: 'request' is identified as a natural-language strategy, and 'confirm' is explained as the switch that triggers a run rather than a preview. For two simple parameters this is adequate, though a format example for request would strengthen it further.

  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 clear action: accept a natural-language strategy request, configure the backtester, and conditionally return a preview or run it. The verb and resource are specific. However, it does not explicitly differentiate from the sibling preview_backtest and run_backtest tools, which appear to offer the same behaviors separately.

  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 natural-language strategy requests but gives no guidance on when to use this combined tool versus calling preview_backtest or run_backtest directly. It does not mention alternatives or exclusion conditions, leaving the agent to guess the correct routing among siblings.

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

• close_browserA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It clearly discloses the primary action ('close the local automation browser') and an important non-destructive detail ('preserving the persistent login profile'), which tells an agent that credentials/session state survive the close. It does not mention secondary effects such as open tabs or reconnection behavior, but for a zero-parameter close operation, this is sufficient.

  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 concise sentence with no filler. The core action is front-loaded, and the key preservation guarantee is included without unnecessary elaboration.

  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?

  For a parameterless tool with no output schema and straightforward behavior, the description is fully complete. It states both what happens (close) and what is preserved (login profile), which is everything an agent needs to invoke it correctly and understand its impact.

  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?

  The input schema has zero parameters, so the baseline is 4. There are no parameter details to add, and the description appropriately focuses on behavior rather than 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 uses a specific verb ('Close') with a clear resource ('the local automation browser') and adds a meaningful qualifier ('while preserving the persistent login profile'). It unambiguously identifies a browser-lifecycle action and is clearly distinct from the backtest-focused sibling tools.

  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 makes the tool's purpose obvious, but it does not explicitly state when it should be called or contrast it with alternatives. Usage timing is implied rather than stated, which fits a simple utility but lacks explicit when-to-use guidance.

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

• get_resultsA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of disclosing behavior. It clearly states the tool reads visible metrics and does not start a new run, signaling a non-destructive read operation. It does not describe error scenarios or preconditions (e.g., what happens if no results are visible), which is a minor gap given the simplicity of the 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 a single concise sentence that front-loads the core action ('Read the currently visible AlgoTest Backtest result metrics') and includes a relevant constraint ('without starting a new run'). Every word earns its place, with no redundancy or fluff.

  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?

  Given the tool's simplicity (no parameters, no output schema), the description is complete for an agent to invoke it correctly. It states what the tool reads and explicitly denies side effects, which is all that is needed for correct usage. There are no missing fields or behaviors that would prevent an agent from using it appropriately.

  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?

  The tool has zero parameters, and the schema coverage is 100% (empty schema). According to the rubric, a baseline of 4 is appropriate when there are no parameters, as there is nothing to add. The description correctly does not mention parameters, and the schema fully defines the input expectations.

  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 'Read', a resource 'currently visible AlgoTest Backtest result metrics', and adds the scope 'without starting a new run', which clearly distinguishes it from siblings like run_backtest and preview_backtest. An agent can readily infer what this tool does and how it differs from the others.

  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 it does not start a new run, implying it is for reading existing results, which is a clear usage constraint. However, it does not explicitly mention when to use it versus alternatives (e.g., after a backtest has been run or previewed), nor does it state prerequisites (e.g., that a run must have already occurred). The context is clear enough for basic usage, but lacks explicit alternative routing.

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