Server Quality Checklist

Tool Scores

• roblox_playtestA
  4.1/5.0
  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 does well describing what each action does (e.g., 'Scripts execute, physics activate' for start, 'return to Edit mode' for stop), but lacks information about permissions needed, rate limits, error conditions, or what happens when actions fail. The description doesn't contradict any annotations since none exist.

  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 well-structured with clear action listings and a workflow summary. Every sentence adds value, though the workflow section could be slightly more concise. The information is front-loaded with the core purpose, followed by detailed actions, then workflow context.

  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 8 actions, 6 parameters, nested objects, and no output schema, the description does an excellent job covering the tool's functionality. It explains what each action does, how parameters relate to actions, and provides workflow context. The main gap is lack of output information (what each action returns), which is significant given the absence of an output schema.

  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?

  With 100% schema description coverage, the baseline is 3. The description adds significant value by explaining parameter usage context: it clarifies which parameters belong to which actions (e.g., 'mode' for start, 'position' and 'lookAt' for move_camera), provides default values ('run' for mode), and explains enum meanings ('run' vs 'play'). This goes well beyond what the schema provides.

  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's purpose as controlling Roblox Studio playtest sessions and interacting with the running game, with specific verbs for each action (start, stop, status, etc.). It distinguishes from siblings by focusing specifically on playtest control rather than general Roblox operations like scene management or scripting.

  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 workflow (start → interact/observe → screenshot → evaluate → stop → fix → repeat) that gives excellent context for when to use this tool. However, it doesn't explicitly state when NOT to use it or mention specific alternatives among the sibling tools, which prevents a perfect score.

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

• roblox_scriptA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it explains that 'execute' runs code in server context, returns results or errors, and requires 'return' statements to get values back. It also mentions script types and parent locations, though it could add more about permissions or 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.

  Conciseness4/5

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

  The description is well-structured with bullet points for actions and clear parameter lists, making it easy to scan. It's appropriately sized with no wasted sentences, though the 'Common parent locations' section could be integrated more tightly with the 'create' action for better flow.

  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 7 parameters, no annotations, and no output schema, the description does a solid job covering key aspects: it explains actions, parameters, and behavioral context like execution environment. However, it lacks details on error handling, response formats, or limitations, leaving some gaps in completeness.

  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 100%, so the baseline is 3. The description adds some value by clarifying parameter usage per action (e.g., 'source' is required for 'create', 'update', and 'execute') and providing examples like common parent paths, but it doesn't significantly enhance meaning beyond what the schema already documents.

  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 performs CRUD operations on Lua scripts in Roblox Studio, specifying 'create, read, update, and execute' with explicit resource targeting. It distinguishes from siblings like 'roblox_get' or 'roblox_scene' by focusing specifically on script manipulation rather than general object retrieval or scene management.

  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 for when to use each action (e.g., 'create' for new scripts, 'read' to view source) and includes practical guidance like common parent locations for script placement. However, it doesn't explicitly state when NOT to use this tool versus alternatives like 'roblox_manage' or 'roblox_toolbox', missing explicit sibling differentiation.

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

• roblox_manageA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it explains what 'reset_pivot' does for debugging, mentions that it's 'automatically done on toolbox insert,' describes property formats with examples, and clarifies that actions like 'delete' destroy instances. However, it doesn't cover error handling, permissions, or rate limits.

  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 appropriately sized and front-loaded with the core purpose, followed by a structured list of actions with their parameters. Every sentence earns its place, though the property format explanation could be slightly more concise. Overall, it's well-organized and efficient.

  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 complexity (9 parameters, nested objects, no output schema, no annotations), the description is quite complete. It covers all actions, parameter semantics, and behavioral context. The main gap is the lack of output information, but this is mitigated by the detailed input guidance. It adequately compensates for the missing structured data.

  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 100%, so the baseline is 3. The description adds significant value by explaining parameter usage per action (e.g., 'className (required)' for create), providing property format examples, and clarifying default values like 'parent (default path)' for create_multiple. This goes well beyond what the schema provides.

  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 clear purpose statement: 'Mutate instances in the Roblox Studio scene.' It specifies the exact action (mutate) and resource (instances in Roblox Studio scene), and distinguishes from sibling tools like roblox_get (likely read-only) and roblox_playtest (likely testing-focused).

  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 for when to use specific actions (e.g., 'Use this when positioning/PivotTo is behaving unexpectedly' for reset_pivot), but doesn't explicitly state when to choose this tool over alternatives like roblox_scene or roblox_toolbox. It offers good intra-tool guidance but lacks inter-tool comparison.

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

• roblox_getA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states the read-only nature upfront, describes what each action retrieves, and provides useful context like default values and parameter purposes. However, it doesn't mention potential limitations like rate limits, authentication needs, or error conditions that would be helpful for a tool with 10 parameters.

  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 well-structured with a clear opening statement followed by an organized action list. Each action is concisely described with its purpose and relevant parameters. While comprehensive, some action descriptions could be slightly more concise (e.g., 'texture_info' has a lengthy explanation). Overall, most sentences earn their place by adding necessary clarification.

  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 10 parameters, 9 actions, and no output schema or annotations, the description does an excellent job of providing context. It explains the tool's purpose, when to use it, what each action does, and how parameters relate to actions. The main gap is the lack of output format information, which would be helpful given the complexity and absence of an output schema.

  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?

  Despite 100% schema description coverage, the description adds significant value by explaining the semantic meaning of each action and how parameters map to specific actions. It clarifies which parameters are used by which actions, provides default values not in the schema, and explains the purpose of complex actions like 'texture_info' with specific use cases. This goes well beyond what the schema provides.

  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 this is for 'read-only queries against the Roblox Studio scene' and specifies the verb 'retrieve' for the actions. It explicitly distinguishes this tool from its siblings by emphasizing its read-only query nature, which contrasts with management, playtesting, scene manipulation, scripting, and toolbox operations implied by the sibling names.

  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?

  The description provides explicit guidance on when to use this tool: for read-only queries, with the 'action' parameter selecting specific retrieval operations. It implicitly distinguishes from siblings by focusing on querying rather than modification, though it doesn't name specific alternatives. The action list serves as a comprehensive menu of when to use each query type.

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

• roblox_sceneA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well. It explains what screenshots return ('PNG image you can analyze visually'), clarifies limitations ('No textures are rendered'), describes camera positioning behavior for both modes, specifies defaults (maxParts=2000, angle=35, yaw=45), and notes constraints ('Both must be provided and must be different points'). It doesn't mention rate limits or authentication needs, but provides substantial 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?

  The description is well-structured with clear sections (overview, actions with sub-modes, typical workflow). Every sentence adds value: the opening states purpose, action descriptions provide specific guidance, and the workflow shows practical application. No wasted words despite the complexity of 7 parameters and multiple operation modes.

  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 7 parameters, no annotations, and no output schema, the description does an excellent job. It explains what the tool does, how to use it, parameter meanings, and provides a workflow. The only gap is not explicitly describing the return format for move_camera (though it's implied to be a camera position change), but given the rich parameter explanations and behavioral context, this is minor.

  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 100%, so baseline is 3. The description adds significant value by explaining parameter semantics beyond the schema: it clarifies that maxParts is for screenshot only, explains the two distinct modes for move_camera with clear examples, describes what angle and yaw actually control, and provides concrete usage examples. This goes well beyond what the schema provides.

  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's purpose: 'Control the camera and capture rendered viewport screenshots.' It specifies two distinct actions (screenshot and move_camera) with their specific functions, and distinguishes from sibling 'roblox_get' by noting that screenshots don't render textures. This provides specific verb+resource differentiation.

  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?

  The description provides explicit guidance on when to use each action: 'Use it to verify placement, scale, orientation, and scene composition' for screenshot, and describes two distinct modes for move_camera. It also provides a typical workflow sequence and explicitly mentions when to use the sibling tool 'roblox_get' for texture context instead.

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

• roblox_toolboxA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden and excels at disclosing behavioral traits. It warns about toolbox models containing 'far more than their name implies' with specific examples, mentions orientation and scale mismatches, provides preference guidance for search results ('Prefer assets where HasScripts=false or IsEndorsed=true'), and explains critical post-insertion steps. This goes well beyond basic parameter documentation.

  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 well-structured with clear action sections and front-loaded critical information. Every sentence earns its place by providing essential guidance, warnings, or clarification. It could be slightly more concise in the 'insert' section where some details are repeated, but overall it's efficiently organized for a multi-action tool.

  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 complex tool with 9 parameters, no annotations, and no output schema, the description provides excellent completeness. It covers all three actions thoroughly, includes critical behavioral warnings, explains parameter usage in context, and provides practical workflow guidance. The only minor gap is lack of explicit return value documentation, but this is reasonable given the tool's scope.

  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?

  With 100% schema description coverage, the baseline is 3, but the description adds significant value beyond the schema. It explains the practical meaning of search parameters (e.g., 'Prefer assets where HasScripts=false or IsEndorsed=true'), clarifies that 'parent' defaults to 'Workspace', and provides context about what 'strip_scripts' actually does ('Remove all scripts from an instance tree'). However, it doesn't fully explain all parameter interactions or edge cases.

  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's purpose with specific verbs ('Search', 'insert', 'sanitize') and resources ('Roblox Creator Store', 'models'). It distinguishes from siblings by focusing on the toolbox/store functionality rather than general Roblox operations like get, manage, playtest, scene, or script tools.

  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?

  The description provides explicit guidance on when to use each action: 'search' for finding assets, 'insert' for placing them, and 'strip_scripts' for cleaning inserted models. It includes critical warnings about toolbox models containing unexpected content and orientation/scale issues, plus specific advice to 'Always inspect the returned hierarchy before building additional objects' and 'Always do this after inserting models with HasScripts=true.'

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