Server Quality Checklist

Tool Scores

• enter_weather_forecast_city_israelC
  2.7/5.0
  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 of behavioral disclosure. It only states that a city name is entered into a search field, but it does not explain whether the field is cleared first, whether typing triggers a dropdown, or whether submission/selection is handled separately. For a UI interaction tool, this is a notable gap.

  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 one short, direct sentence in Hebrew with no wasted words. It is appropriately sized for a simple action, though it sacrifices potentially useful detail for 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?

  The description omits surrounding workflow context, such as the need to first open the weather page and then select the matching city suggestion after entering text. Although an output schema exists and the action is simple, the lack of step linkage makes it incomplete for an agent navigating a multi-step process.

  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 zero description coverage for the only parameter, city_name. The tool description restates that the city name is entered but adds no formatting, language, or example constraints. It confirms the parameter's purpose but does little to clarify expected values beyond the schema property name.

  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 clear action verb ('מזין' = enters/types) and specifies the target ('the search field on the site'), making the tool's basic purpose understandable. It does not explicitly distinguish itself from the sibling select tool, but the action of entering text is distinct enough from selecting a suggestion.

  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?

  There is no guidance on when to use this tool versus its siblings (open, select, extract). The reader must infer that it fits between opening the forecast page and selecting a city, but the description does not state this workflow context or mention any alternatives.

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

• extract_weather_page_contentA
  3.5/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It states the action (extract text) but does not mention whether this is read-only, if it has side effects, requires specific page state, or has rate limits. No additional behavioral traits are surfaced beyond the literal meaning.

  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 in Hebrew that front-loads the verb and clearly states the object. Every word earns its place 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?

  The tool has an output schema and no parameters, so the description is fairly complete for a simple extraction action. However, it lacks integration context with sibling tools (e.g., when to call it after navigation) and does not mention edge cases like 'no page loaded.' This leaves minor but clear gaps.

  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?

  There are zero parameters, so the schema is complete by default (100% coverage). The description adds no parameter meaning, but none is needed. Baseline for 0 parameters is 4, which is appropriate here.

  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 ('מחלץ' / extracts) and identifies the resource ('תוכן הטקסט מהעמוד הנוכחי' / text content from the current page) along with the beneficiary ('עבור ה-LLM' / for the LLM). This clearly distinguishes it from sibling tools that focus on weather forecast navigation.

  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 relative to its siblings, such as 'call after entering a city' or 'use this instead of X when you need the page text.' The description simply states what it does without any contextual usage advice.

  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
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It states the primary action (opening the browser and navigating), which is transparent. But it does not mention any side effects, such as browser persistence, page-load waiting, or whether it returns anything. Additional context would improve transparency, but the description is not misleading.

  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, clear sentence with no wasted words. It is appropriately sized for the tool's simplicity and front-loads the key action.

  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 (zero parameters, no annotations), the description is mostly complete. The presence of an output schema reduces the need to explain return values. However, lacking any guidance on how this fits into the sibling workflow (e.g., 'start here') makes it slightly less complete, but not significantly so.

  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, so the baseline is 4. The description correctly makes no mention of parameters because there are none to explain. The input schema already confirms an empty properties object, so no additional meaning is needed.

  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 specific verb+resource: 'opens the web browser and navigates to the weather forecast website in Israel.' This distinguishes it from sibling tools like extract_weather_page_content, which extracts content, and enter_weather_forecast_city_israel, which enters a city.

  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 does not explicitly state when to use this tool versus alternatives. However, the sibling names imply it is the initial step in a weather forecast workflow. No explicit exclusions or alternative guidance is provided, so usage context is only implied.

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

• select_weather_forecast_city_israelA
  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 must carry the behavioral disclosure burden. It accurately describes the core action but does not mention potential side effects, prerequisites (e.g., dropdown must be open), or failure behaviors. For a simple UI selection step, 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?

  One short sentence, front-loaded with the verb and object. No wasted words, easy to parse quickly.

  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, the description is nearly complete. It states the action and its triggering condition (search already done). The output schema exists, so return values are covered elsewhere. It could mention the need for the dropdown to be present, but that is implied by 'opened following the search'.

  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 0 parameters, so the baseline is 4. The description adds no parameter semantics because there are none to describe; nothing is needed 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 a specific action ('selects the first result') on a specific resource ('the dropdown list that opened following the search'). This distinguishes it from sibling tools like 'open_weather_forecast_israel' and 'enter_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 Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies the tool is used after a search has opened a dropdown ('following the search'), providing clear context. However, it does not explicitly name the sibling tool to use before it or state 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.