Server Quality Checklist

Tool Scores

• set-bcf-viewA
  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 full burden. It discloses key behaviors: it only sets view state in an already-open viewer, does not show/load IFC files, should not open a new tab, and should not use browser automation. It also implies a prerequisite (viewer must be open). However, it does not mention return values or error handling, which would contribute to full transparency.

  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 core description is concise and front-loaded, with the first sentence stating purpose and the next clarifying input. The long code example earns its place by showing a complete workflow, but it adds length. Overall, it is well-structured and not wasteful, though it could be slightly tighter without losing value.

  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 simple schema (one param, no output schema) and lack of annotations, the description provides adequate context: purpose, input types, exclusions, and a full usage example. It even gives a Python code sample for generating the BCFZIP. However, it stops short of explaining the tool's return value or potential errors, which is a minor gap for an otherwise clear description.

  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% for the single parameter, so the baseline is 3. The description repeats the same information about accepting a local path or generated URL, but adds little beyond the schema description. The code example illustrates usage but does not substantially enhance parameter understanding beyond what the schema already 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 function: 'Set the view state in the already-open local IFC viewer by applying a BCF/BCFZIP viewpoint file.' It uses a specific verb ('set'), identifies the resource ('view state in viewer'), and explicitly distinguishes from siblings by stating 'This tool does not show/load IFC files; use show-ifc-file for that.'

  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 when-to-use and when-not-to-use guidance: it says not to use for showing/loading IFC files and points to show-ifc-file as the alternative. It also explains a workflow with run-python to generate the BCFZIP and how to pass the URL, giving clear context for when this tool is appropriate.

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

• clear-ifc-viewerA
  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 burden of behavioral disclosure. It states that the operation removes all loaded files and viewpoint state, keeps the same stable viewer URL, and does not close the browser tab. These are meaningful behavioral traits that go beyond the tool's name, though it does not address reversibility or potential side effects like confirmation prompts, which are not critical for a clearing operation.

  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 extremely concise, consisting of two sentences that directly communicate the action, its scope, and the recommended next step. There is no wasted phrasing; each clause adds value. The structure front-loads the primary function and then adds relevant context.

  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. It clearly explains what state is cleared, what remains unchanged, and how to proceed with a fresh model. The mention of show-ifc-file provides essential workflow context, making the tool's place in the larger process clear.

  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 input schema is empty, so parameter semantics are trivially satisfied. According to the rubric, 0 parameters baseline is 4, and the description does not need to add parameter details. The description appropriately focuses on the action and outcome.

  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 function with a specific verb ('Clear') and resource ('already-open local IFC viewer'), and precisely describes what it does: removing all loaded IFC files and BCF viewpoint state. It also differentiates from siblings by noting it keeps the same stable viewer URL and does not close the browser tab, which distinguishes it from open-ifc-viewer and show-ifc-file.

  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 (already-open viewer) and explicitly directs the next step: 'Use show-ifc-file after this to load a fresh IFC model.' However, it does not explicitly mention when not to use it or compare with other siblings like open-ifc-viewer or set-bcf-view, though the primary use case is well conveyed.

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

• run-pythonA
  4.5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden. It discloses the Pyodide version (0.28.2), the available package set, file path behavior differences in desktop vs browser hosts, and the return contract including stdout, stderr, saved_files, uploaded_files, and the fact that generated files are temporary URLs rather than written to the user's directory. This is highly transparent.

  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 organized into four short paragraphs, each earning its place: purpose, runtime context, file inputs, and return contract. It is concise yet comprehensive, with no redundant or vague sentences.

  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 code execution tool with no output schema, the description adequately covers runtime details, package availability, file path resolution in different hosts, and the exact return structure including URL handling. It provides enough context for an agent to invoke the tool correctly and interpret results.

  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?

  All three parameters (code, files, timeout_seconds) are fully described in the schema, giving 100% coverage. The description adds general runtime context but does not add meaning beyond what the schema already states for each parameter. The baseline of 3 is appropriate.

  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 'Execute' with a clear resource: 'LLM-created Python in the SDK Node/Pyodide IFC runtime.' It lists concrete use cases (IFC inspection, validation, reports, exports, creating IFC files) and differentiates from sibling viewer tools by emphasizing code execution rather than visualization.

  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 states 'Use this tool for IFC inspection, validation, reports, exports, and creating new IFC files,' providing clear context for when to invoke it. It does not explicitly exclude alternatives or name viewer tools as alternatives, but the sibling names make the distinction obvious. This earns a 4 rather than 5.

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

• show-ifc-fileA
  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 full burden and does well: it discloses that the viewer must already be open, that calls can repeat and add files, and that it returns a stable viewer URL to use afterward. It does not mention potential failure modes or file size limits, but the key behavioral traits are clear.

  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?

  Each sentence earns its place: it states the action, the accepted inputs, the usage scope, the repeated-call behavior, the return value, and cross-references to sibling tools. It is front-loaded with the primary purpose and entirely free of 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 moderate complexity, a single parameter, and no output schema, the description is complete. It explains the return value (stable viewer URL), how to use the result, and how it fits into the workflow with the sibling tools, leaving no necessary context missing.

  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 already fully describes the single parameter at 100% coverage. The description adds valuable context by explicitly tying the file_path to 'run Python saved_files' generated URLs and listing the supported IFC formats, going slightly beyond the schema text.

  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 and resource: 'Show one IFC file in the already-open local IFC viewer.' It clearly distinguishes itself from siblings by explicitly noting that open-ifc-viewer is for opening the viewer and set-bcf-view is for applying BCF viewpoints.

  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 gives explicit when-to-use guidance ('Use this for IFC model display only') and names alternatives and complementary tools (open-ifc-viewer, set-bcf-view). It also clarifies that repeated calls add multiple files, which is a key usage constraint not otherwise inferable.

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

• open-ifc-viewerA
  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 full burden. It discloses non-behaviors (does not load files, does not alter selection/isolation), states the output is a stable URL, and gives post-return instructions. This is thorough behavioral disclosure for a zero-parameter 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 about 100 words but every sentence adds value: purpose, non-goal clarification, usage instructions for the returned URL, sibling references, and an explicit prohibition. It is front-loaded with the primary purpose and remains structured without 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?

  Given the tool's simplicity (no params, no output schema), the description fully covers its function, limitations, and integration with sibling tools. It leaves no ambiguity about what the tool does or how to proceed after invocation, making it complete for its complexity.

  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 is empty. The baseline for zero params is 4, and there is no need for the description to explain parameters. The description adds no parameter info, but none is required.

  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 opens/shows the local IFC viewer and returns its stable viewer URL. It explicitly differentiates from siblings by noting it does not load IFC files or change selection/isolation state, and references show-ifc-file and set-bcf-view for those purposes.

  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?

  Explicit guidance is given: use this tool for opening the viewer, use show-ifc-file to display IFC files, use set-bcf-view to apply BCF viewpoints. It also instructs what to do with the returned URL and warns against browser automation for clicking/selecting, providing clear when-to-use and when-not-to-use context.

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