Server Quality Checklist

Tool Scores

• generate_sceneA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It discloses two important behavioral traits: it consumes real LLM budget (bounded) and takes minutes. However, it doesn't mention whether the scene is persisted, whether a session is created, or any side effects on existing state, leaving partial transparency.

  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: the first identifies the purpose, the second adds critical cost/time caveats. Every word earns its place, and the most important information is front-loaded.

  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 has an output schema, return values are covered elsewhere. The description explains the pipeline, budget, and duration, which are essential contextual warnings. It could mention how this relates to sessions (since siblings manage sessions), but overall it is reasonably complete for a generation action.

  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?

  Schema description coverage is 0%, and the description provides no explanation of 'prompt' or 'scene_type'. It merely says 'from a prompt,' but does not elaborate on prompt format, required content, or how scene_type affects output. The description does not compensate for the schema's lack of descriptions.

  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 'Generate a sim-ready Isaac USD scene from a prompt,' which uses a specific verb and resource, clearly distinguishing this tool from siblings like list_categories or get_session_report that handle retrieval rather than creation.

  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 states the high cost and long duration ('spends real LLM budget... takes minutes'), giving clear context that this is a heavy operation. It does not explicitly name alternatives or exclusions, but the cost/time warning strongly implies use only when a full scene is needed.

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

• get_session_reportA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. The verb 'Fetch' implies a read-only operation, but the description does not explicitly state it is non-destructive or mention requirements like authentication or error behavior. It does add value by specifying what the report contains (status, quality, full report).

  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 directly communicates the tool's function without unnecessary words or repetition. It 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 output schema exists, so return values are covered, but the description lacks guidance on usage context and parameter semantics. For a simple fetch tool, it is minimally adequate but leaves gaps around prerequisites and sibling tool differentiation.

  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?

  With 0% schema description coverage, the description must compensate for the parameter `scene_hash`, but it merely restates the parameter name without explaining what a scene hash is or how to obtain it. This is insufficient for an agent to correctly populate the parameter.

  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 ('Fetch'), the resource ('session report'), and the scope ('for a scene hash'). It also lists the key content (status, quality, full report), which distinguishes it from sibling tools like list_sessions.

  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 clearly indicates the tool is used to retrieve a session report for a specific scene hash. It does not explicitly exclude alternatives or provide when-to-use guidance, but the context is clear enough for an agent to select it when report details are needed.

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

• list_sessionsA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It describes a read-only operation ('List') and indicates the output fields, but it does not disclose potential behavioral traits such as pagination, ordering, authentication requirements, or whether any side effects exist. For a simple listing tool, the lack of mutation is implied, but more transparency would be better.

  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 sentence that is front-loaded with the action ('List every generated session') and includes useful specifics about the output fields. Every word earns its place; there is no 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?

  The tool is simple (no parameters) and has an output schema that presumably defines the return structure, so the description need not explain return values. It sufficiently conveys that it lists all sessions with specified fields. However, it does not mention sorting, pagination, or how this relates to sibling tools like get_session_report, which could add completeness.

  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 schema covers everything trivially. The description correctly omits parameter details since there are none. The baseline for 0 parameters is 4, and the description does not need to add anything further.

  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 ('List') and a clear resource ('every generated session'), and even specifies the fields shown ('scene hash, status, quality'). This clearly distinguishes it from sibling tools like list_categories (different resource) or get_session_report (likely a single session report).

  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 phrase 'List every generated session' implies the tool is used when you need a broad overview of all sessions, distinguishing it from more specific tools like get_session_report. However, it does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions or prerequisites. Usage is inferred rather than explicitly guided.

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

• retrieve_articraftA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It discloses that query ranks records and 'omit to keep catalog order,' that each record is a URDF asset with meshes and joints, and that it returns 'ranked records with their ids and metadata.' This goes beyond the basic 'retrieve' verb and reveals the internal behavior and return shape, though it doesn't mention error handling 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.

  Conciseness5/5

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

  The description is well-structured with a first sentence summary, a brief explanation of record composition, and an Args section that enumerates parameters. Every sentence earns its place, and the format is scannable. It is neither too terse nor bloated.

  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 simple parameter set, presence of an output schema, and clear sibling relationships, the description covers purpose, prerequisites, parameter semantics, and return content. It fully explains the workflow and leaves no critical gaps 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.

  Parameters5/5

  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, and it does. It explains category as an exact slug from list_categories, query as free-text for ranking with an omission behavior, and top_k as the maximum number of records. All three parameters are clearly defined beyond their schema 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 specific verb and resource: 'Retrieve articulated furniture records from one catalog category.' It clearly distinguishes from siblings by referencing list_categories for slugs and generate_scene for placement, showing where this tool fits 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?

  It gives explicit prerequisite guidance: 'Use list_categories first to find valid category slugs.' It also explains that the records are intended for generate_scene to place, providing clear context on when to use it. It doesn't name alternative retrieval tools or state 'when not to use,' but the guidance is sufficient for selecting this tool.

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

• list_categoriesA
  4.8/5.0
  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. It discloses the return structure ('each with its record count') and the case-insensitive substring filtering behavior, which gives a clear sense of what the tool does without side effects. However, it does not explicitly state that the operation is read-only or describe potential edge cases (e.g., invalid inputs, empty results), so it is not fully transparent but still strong.

  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: main purpose, return value, args, and returns. Each sentence earns its place, with no redundant fluff. It is front-loaded with the most important information and uses a clean format for parameter details.

  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 has one optional parameter, a clear output schema, and a well-defined use case, the description is complete. It explains what the tool returns, how to filter, and how it relates to sibling tools. The presence of an output schema means return format details are covered elsewhere, so the description does not need to over-explain.

  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?

  Even though the schema only lists 'contains' as a nullable string, the description enriches it substantially: 'Case-insensitive substring filter on the category slug; omit to list every category.' This explains the exact semantics, case-sensitivity, and the effect of omission, providing high value 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 opens with a specific verb+resource: 'List the articulated-furniture categories in the articraft catalog.' It clearly states the tool's scope and function, and distinguishes it from sibling tools by naming the related tool 'retrieve_articraft' and positioning this as the prerequisite discover step.

  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?

  Provides explicit guidance: 'Call this before retrieve_articraft to discover valid category names.' It also tells the user how to use the 'contains' parameter ('omit to list every category'), covering both the recommended use and the alternative behavior, which effectively communicates when to use this tool versus others.

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

• resume_sessionA
  4.9/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries the full burden. It discloses key behaviors: re-runs the pipeline from start_stage, writes a new revision while leaving prior revisions untouched, spends 'real LLM budget' and 'takes minutes.' It also details the return values, offering significant transparency beyond a minimal description.

  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 front-loaded with a purpose sentence and then uses a concise Args block for parameters. While a little longer than strictly necessary, each sentence provides actionable information and there is no 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 covers prerequisites (checkpoints on disk), cost/time tradeoffs, alternative tools, parameter semantics, and return values. Given the tool's moderate complexity and the absence of annotations/output schema detail, the description is thoroughly complete.

  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 provides no descriptions (0% coverage), but the tool description documents every parameter in the Args section: scene_hash is sourced from list_sessions or generate_scene, start_stage lists valid stage values, and stop_stage explains optionality and default behavior ('omit to run to the end'). This fully compensates for the schema gap.

  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 verb-resource pair: 'Resume an existing generation session from a stage checkpoint.' It clearly states the tool's primary function and distinguishes it from the sibling generate_scene by noting it is 'Cheaper than generate_scene when only later stages need to change.'

  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 prefer this tool over generate_scene, saying it is cheaper when only later stages need to change. It also indicates that it uses checkpoints already on disk, and mentions that scene_hash comes from list_sessions or generate_scene, providing clear usage context and alternatives.

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