Server Quality Checklist

Tool Scores

• select_weather_forecast_city_israelA
  4.1/5.0
  Behavior4/5

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

  No annotations are provided, so the description bears full responsibility for disclosing behavior. It reveals a key detail: the first autocomplete item is not always the city itself, recommending text matching for correct selection. It also states that clicking loads the forecast page, providing sufficient transparency for the primary action, though edge cases are not 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 concise, with a single-sentence purpose followed by a focused explanation of the sole parameter. It is front-loaded and every sentence adds valuable information without redundancy or filler.

  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 tool with one parameter and no annotations, the description covers purpose, parameter semantics, and a behavioral caveat. The presence of an output schema means return values need not be explained. It lacks explicit timing relative to sibling tools but is otherwise complete for its simplicity.

  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?

  The input schema only lists 'index' with a default and no description (0% schema coverage). The description thoroughly explains the parameter: it is zero-based, defaults to 0, and warns that the first item may not be the city, advising preference for matching text. This fully compensates for the schema's lack of information.

  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 'Click a city from the autocomplete list and load its forecast page', specifying a specific action and resource. It differentiates from sibling 'enter_weather_forecast_city_israel' by focusing on selection rather than typing, but does not explicitly contrast with all siblings, preventing a perfect score.

  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 it should be used when an autocomplete list appears after entering a city, noting the first item may not be the desired one. It advises selecting the index whose text matches the user's request, which is helpful but not explicit about when to choose this over 'enter' or 'open' siblings. Usage context is implied rather than clearly delineated.

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

• close_weather_browser_israelA
  4.3/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses that the tool is safe to call at any time, which is useful behavioral context. However, it does not explain potential side effects (e.g., discarding unsaved browser state) or behavior if the browser is already closed. Still, for such a simple 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?

  The description is a single, brief sentence that front-loads the core action ('Close the browser opened by these tools') and adds a safety note, with no redundant information. It earns its place perfectly.

  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 extremely simple (no parameters, no complex logic) and has an output schema. The description clarifies both the operation and its safety, and the sibling tools provide context for when this cleanup action is needed. Nothing else is required 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.

  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 confirms this (empty properties). With no parameters to document, the description does not need to add parameter details. Per the rubric, a zero-parameter tool receives a baseline score of 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 uses a specific verb ('close') with a clear resource ('the browser opened by these tools'), immediately distinguishing this from sibling tools that open, enter, select, or extract forecast data. Even without naming the sibling tools, 'these tools' makes the scope 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?

  The phrase 'Safe to call at any time' provides explicit guidance on when the tool can be used, implying it is a cleanup action with no risk. It does not explicitly compare to alternatives, but the tool's purpose is evident and complements the sibling tools, making this clear enough for an agent.

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

• open_weather_forecast_israelA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden. It openly discloses a stateful side effect (leaves browser sitting on forecast page) and return values (page title and URL). However, it does not clarify browser lifecycle details (e.g., whether multiple calls open new tabs or how the browser is reused), which could be inferred from siblings but are not explicit.

  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 compact sentences: first states the primary action, second adds usage guidance and return info. Every sentence earns its place with no redundant content.

  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 a simple first step in a larger workflow. The description covers action, resulting state, and return values, and the output schema (mentioned in signals) exists. Given sibling tools handle later steps, the context is complete.

  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?

  Tool has zero parameters, so the empty schema is self-explanatory. Baseline of 4 applies, and the description need not add parameter semantics since there are none.

  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 action (open a browser and navigate) with a specific resource (Israeli weather forecast site). It distinguishes itself from sibling tools by describing the initial navigation step and leaving the search box ready, which is unique among the 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 instructs 'Call this first,' providing clear timing relative to alternatives. Also describes the resulting state (city search box ready), which implies subsequent tools like enter_weather_forecast_city_israel should follow, giving effective 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.

• extract_weather_forecast_israelA
  4.8/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden. It discloses that the tool reads the current page, returns clean markdown, and that defaults include current conditions plus three days of hourly forecast. It also explains the consequence of shrinking the window and parameter clamps. It doesn't mention error handling or exact output schema, but the output schema exists to cover that.

  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: a one-line action, then workflow context, then default behavior, then parameter details. Every sentence earns its place, and the warning about shrinking the window is concise yet impactful. 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?

  The description fully situates the tool in its workflow, explains the default return content, and specifies how parameters affect output. Since an output schema exists, return value details are covered. It also gives clear prerequisites (page open, after select step). No significant gaps.

  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 0%, but the description fully compensates. It explains each parameter's purpose ('Days of hourly forecast'), when to leave unset, and clamping ranges. It also adds strategic guidance: 'Shrinking the window costs you the data you are about to be asked about.' This is rich, actionable semantics beyond the bare 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 starts with a specific verb-resource pair: 'Read the forecast off the page that is currently open, as clean markdown.' This clearly states what the tool does and distinguishes it from siblings like open_weather_forecast_israel or select_weather_forecast_city_israel by tying it to the current page and markdown output.

  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?

  It explicitly states when to use it: 'Call this after select_weather_forecast_city_israel.' It also tells the agent to call it with NO arguments and warns against shrinking the window, providing clear context. Parameter guidance ('Leave unset unless the user explicitly asks about several days ahead') further clarifies usage.

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

• enter_weather_forecast_city_israelA
  5/5.0
  Behavior5/5

  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 returns autocomplete suggestions numbered from 0, may include non-city results, and provides a concrete example ("חיפה" yielding "חוף הסטודנטים, חיפה" first). This is rich, actionable behavioral context.

  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 succinct sentences cover the action, return behavior, and next step, plus a clear Args section. Every sentence earns its place; no fluff or redundancy.

  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 one-parameter tool with an output schema (not shown), the description covers the action, return semantics, caveats, and the follow-up call. It is fully complete for guiding correct tool invocation within the sibling workflow.

  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?

  The schema only defines 'city' as a string with no description. The description adds that the city name must be in Hebrew and provides examples (תל אביב, חיפה, באר שבע), which is critical for correct input and 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 states a specific action ('Type an Israeli city name into the forecast search box') with a clear verb and resource. It distinguishes from siblings by describing the initial entry step, leaving selection to select_weather_forecast_city_israel.

  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 instructs to 'Read the list before choosing, then call select_weather_forecast_city_israel', defining the workflow and when to use this tool. It also warns about neighbourhoods and landmarks, helping the agent interpret results correctly.

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