Server Quality Checklist

Tool Scores

• check_cf_complianceB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses that the tool performs basic CF checks and returns a JSON string report, which is useful. However, it does not mention side effects, error behavior, or that it is read-only, leaving some behavioral expectations unstated.

  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 short and front-loaded with the purpose, followed by clearly labeled Args and Returns sections. It is efficient and easy to scan, though slightly docstring-like rather than optimized for AI agent consumption.

  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?

  For a simple one-parameter tool, the description covers what it does and what it returns. However, it lacks guidance on when to use it versus check_data_quality, and provides no detail about what the compliance report includes. The output schema may cover return structure, but the missing usage context keeps it from being 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?

  Schema description coverage is 0%, so the description must compensate. The Args section explicitly explains that file_path is the path to the NetCDF file, which gives meaning beyond the schema's bare type/title. This is sufficient for the single parameter.

  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 identifies the operation: checking whether a NetCDF file follows CF conventions, which is a specific verb and resource. It is distinguishable from sibling tools like get_file_structure and get_variable_stats, though it does not explicitly differentiate itself from check_data_quality.

  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?

  The description gives no explicit guidance on when to use this tool versus alternatives such as check_data_quality or explain_variable. It states that it performs 'basic checks', but does not say when a user should prefer this over other validation or inspection tools.

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

• compare_variablesB
  3.3/5.0
  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 clearly states the comparison dimensions and that it returns a JSON string, but it does not explicitly confirm the operation is read-only, describe error behavior, or mention what happens if variables are incompatible.

  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 tightly written and front-loaded with the core purpose. The Args and Returns sections provide necessary information without redundant or promotional language, and every sentence 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 description is adequate for invoking the tool, but it lacks usage context, explicit safety assurances, and details about the comparison output beyond 'JSON string.' With no annotations and no visible output schema, slightly more context would make it complete.

  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 0%, but the description adds basic meaning for all three parameters: file_path is a NetCDF path, variable1 is the first variable, and variable2 is the second. It does not add format details, validation constraints, or clarify that variable names must match file contents exactly.

  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 states a specific verb and resource: compare two variables for shape compatibility, range differences, and correlation. This is distinct from sibling tools like get_variable_stats or get_variable_info, though it does not explicitly name a differentiating sibling.

  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 alternatives. It does not mention exclusions, prerequisites, or sibling tools such as get_variable_stats or explain_variable that might perform related analyses.

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

• check_data_qualityB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral disclosure burden. It does state the return type ('JSON string with data quality report') and the kinds of issues detected, but it does not disclose read-only behavior, thresholds, handling of missing variables, or what counts as a 'suspicious pattern'.

  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 compact and front-loaded, with clear Args and Returns sections and no filler. It earns a strong score for structure; it loses one point only because the parameter explanations are thin and could add useful detail without becoming verbose.

  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?

  For a two-parameter analysis tool with an output schema, the description covers the essential invocation details: what file to point at, what variable to check, and what kind of result is returned. It is not fully complete because the semantics of 'suspicious patterns' and outlier detection are left undefined, forcing the agent to discover behavior at call time.

  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 0%, so the description's Args section is the only parameter documentation. It adds minimal but real meaning: file_path is a path to a NetCDF file, and variable_name is the variable to check. It does not specify how to locate the variable within the file or validate it, but the basic semantics are sufficient for correct parameter identification.

  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 opens with a specific verb and resource ('Check a variable for data quality issues') and enumerates concrete checks: NaN/missing values, outliers, and suspicious patterns. This makes it distinguishable from statistical or structural sibling tools, though it never explicitly names an alternative.

  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 phrasing implies this tool should be used when an agent needs a quality assessment rather than statistics, metadata, or variable explanations. However, there is no explicit when-to-use vs. when-not-to-use guidance and no mention of how it compares to close siblings like get_variable_stats or check_cf_compliance.

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

• get_variable_infoA
  3.6/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the behavioral burden. It does disclose the return content and JSON string format, which strongly suggests a read-only operation. However, it does not describe behavior on invalid paths, missing variables, potential errors, or resource implications.

  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 concise, front-loaded with the core purpose, and organized into clear Args and Returns sections. There is minor redundancy between the opening sentence and the Returns line, but otherwise every part is purposeful.

  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 simple two-parameter inspection tool, the description provides enough information to select and invoke it correctly, and the presence of an output schema covers return structure details. It is not fully complete because it omits error behavior and explicit usage guidance relative to sibling tools.

  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 provides no description coverage, so the description must compensate. The Args section does this by explaining file_path as 'Path to the NetCDF file' and variable_name as 'Name of the variable to inspect,' adding the semantic meaning missing from the schema.

  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 identifies the operation as retrieving detailed information about a specific variable in a NetCDF file, and it enumerates the returned fields (dtype, shape, dimensions, attributes, fill value). This distinguishes it from statistical or sample tools in intent, but it does not explicitly call out sibling alternatives.

  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 use when a caller needs variable metadata rather than statistics, samples, or explanations, but it never explicitly states when to use this tool versus its siblings. No exclusions or preferred alternatives are mentioned.

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

• get_file_structureA
  3.7/5.0
  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 of behavioral disclosure. It states the return type (JSON string) and the content of the returned structure, and 'Get' implies a read-only operation, but it does not mention error behavior, file access requirements, or potential performance limitations.

  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 concise and structured with a clear opening summary followed by Args and Returns sections. Every line serves a purpose, and the main function is front-loaded. Minor redundancy exists between the opening line and the Returns section, but it is not wasteful.

  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 simple single-parameter read-only tool with an output schema, the description covers the input parameter, the output format, and the returned content. It does not explicitly differentiate from the many sibling tools, but the 'complete structure' framing makes its role fairly clear. Missing error handling and edge-case guidance, but overall it is complete enough for basic invocation.

  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?

  The input schema provides no description for file_path (0% coverage), so the description's 'Path to the NetCDF file' is the only semantic guidance. It correctly explains the parameter's role but lacks further detail such as accepted path formats, whether remote paths are supported, or file extension expectations, making it minimally sufficient for a single 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 uses a specific verb 'Get', names the resource as 'the complete structure of a NetCDF file', and explicitly enumerates the contents returned (dimensions, coordinates, data variables, global attributes). This clearly distinguishes it from sibling tools like list_variables or get_global_attributes, which focus on individual parts.

  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 'complete structure' implies it is the umbrella tool for a whole-file overview, but the description does not explicitly state when to use this tool versus siblings like get_variable_info or get_dimension_values. There is no when-to-use or when-not-to-use guidance, leaving the agent to infer the intended scope.

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

• get_spatial_boundsA
  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 full burden of explaining behavior. It does disclose that the return value is a JSON string containing spatial bounds, which is useful. However, it does not mention edge cases, coordinate system assumptions, or what happens if the file has no spatial coordinates.

  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 short, front-loaded with the main purpose, and includes an organized Args/Returns structure. Every sentence contributes useful information and 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?

  For a single-parameter, read-only tool, the description covers the essential input and output. The existence of an output schema reduces the need to detail return structure further, and the description is adequate 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.

  Parameters2/5

  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. The Args section says only 'file_path: Path to the NetCDF file', which adds minimal meaning beyond the parameter name and type. It does not specify accepted formats, required variables, or any file constraints.

  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 ('Get') and resource ('geographic extent (lat/lon bounds) of a NetCDF file'). This clearly differentiates it from sibling tools like get_time_range or list_variables, which target different aspects of the file.

  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 when to use the tool: when an agent needs the lat/lon bounding box of a NetCDF file. However, it provides no explicit guidance about when not to use it or which sibling tool might be more appropriate, so the usage context is inferred rather than stated.

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

• get_variable_statsA
  3.8/5.0
  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 explaining behavior. It states that the tool computes a statistical summary and returns a JSON string, which is the core functional behavior. However, it does not explicitly note that the operation is read-only, how it handles missing or non-numeric variables, or whether large datasets could be expensive to process.

  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 compact and front-loaded, starting with a clear one-sentence purpose and then listing parameters and return type. Every line serves a purpose, and the Args/Returns structure makes the content easy to scan without redundant 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 simple two-parameter read-only tool that has an output schema, the description supplies the essential purpose, parameter meanings, and return type. The only notable gap is the absence of explicit sibling-tool differentiation or a note about when this tool should be used versus related analysis tools.

  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?

  The schema has 0% description coverage, so the description must compensate. It does so minimally by explaining file_path as a path to a NetCDF file and variable_name as the variable to analyze. This adds meaning beyond the bare schema titles, but it lacks detail about constraints such as requiring a numeric variable or the variable needing to exist in the file.

  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 verb and resource: it gets a statistical summary of a variable, and enumerates the exact statistics (min, max, mean, std, NaN count, percentiles). This distinguishes it from sibling tools like get_variable_info or get_variable_sample, which focus on metadata or raw sample values.

  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 usage when a statistical summary is needed, but it does not explicitly say when to prefer this tool over alternatives such as get_variable_info or get_variable_sample. There is no comparative guidance or exclusion criteria, leaving the agent to infer the appropriate context from the purpose.

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

• list_variablesA
  3.8/5.0
  Behavior4/5

  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 clearly indicates a read-only listing operation and discloses the return format as a JSON string with variable names, shapes, dtypes, and units. It does not discuss error handling or file-access details, but that is acceptable for this simple 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 compact and front-loaded with the core purpose. The Args and Returns sections are useful and contain no filler or redundant information.

  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 simple parameter and an output schema, the description adequately covers the input and the return content. It lacks sibling differentiation, but that gap is more relevant to usage guidelines than to overall 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 coverage is 0%, but the only parameter is self-explanatory. The description adds that file_path is a path to a NetCDF file, which is marginally more specific than the schema's 'File Path' title, but it does not provide format constraints or other meaningful semantics.

  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 ('List all data variables'), a clear resource ('NetCDF file'), and the exact metadata returned (shapes, dtypes, units). This distinguishes it from sibling tools like get_variable_info, which focuses on a single variable.

  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?

  The description provides no guidance about when to use this tool versus alternatives such as get_file_structure or get_variable_info. It also does not mention any exclusions or preferred scenarios, leaving the agent to infer usage context.

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

• explain_variableA
  3.9/5.0
  Behavior3/5

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

  The description discloses that the tool relies on standard_name, long_name, units, and other attributes, and that it returns a JSON string. It does not explicitly state read-only behavior or failure modes, but the tool's purpose strongly implies no side effects. With no annotations, this is moderate disclosure.

  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 definition is compact and well-organized: a clear purpose sentence, a short mechanism sentence, and distinct Args and Returns sections. There is no redundant or filler content; every line contributes useful information.

  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, just two string parameters, and the existence of an output schema, the description provides the essential information needed to call it. It lacks edge-case behavior and explicit sibling context, but these are not critical for a straightforward explain operation.

  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 fully compensates by defining both parameters: file_path as the path to the NetCDF file and variable_name as the variable to explain. This adds the semantic meaning the structured schema lacks.

  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 specific verb ('Generate') for a clear resource ('a variable') and specifies the output as a 'human-readable explanation.' It also details the attributes used, which helps differentiate it from sibling tools like get_variable_info, though it does not explicitly name them.

  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?

  Usage is implied: call this when you need a natural-language explanation of a variable rather than raw metadata. However, it does not explicitly state when not to use it or name alternatives, leaving the agent to infer the choice among the many sibling tools.

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

• get_global_attributesA
  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 burden of behavioral disclosure. It does disclose the return format ('JSON string') and gives expected content (title, institution, history, conventions, other file-level metadata). However, it does not mention error behavior, file existence requirements, or that this is a read-only operation, leaving some ambiguity.

  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 and well-structured: a one-sentence summary, a content overview, and a clear Args/Returns breakdown. There is no redundant or filler text, and the key purpose 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?

  For a simple tool with one required parameter, an output schema, and a clear return description, the definition is largely complete. The main gaps are the absence of edge-case behavior (missing file, invalid NetCDF) and lack of explicit guidance around when to prefer sibling tools, but these are minor given the tool's simplicity.

  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 schema covers 0% of parameter semantics, but the description compensates with an explicit Args section: 'file_path: Path to the NetCDF file.' This adds real meaning beyond the schema's type-only definition, though it could include more detail about valid path forms or file accessibility.

  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 verb 'Get' with a specific resource ('all global attributes (metadata) from a NetCDF file'), and lists representative contents like title, institution, and conventions. This makes the tool's purpose immediately distinguishable from sibling tools that focus on variables, dimensions, or spatial bounds.

  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 usage when file-level metadata is needed, but it does not explicitly contrast with sibling tools such as get_file_structure or get_variable_info, nor does it state when not to use this tool. The context is clear enough for inference, but no direct routing guidance is given.

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

• get_variable_sampleA
  4.1/5.0
  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 behavioral burden. It discloses the return format ("JSON string with sample values and their indices") and the max_samples cap, indicating a read-only extraction. However, it does not explain how the sample is selected or what happens on errors such as a missing variable.

  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 compact and front-loaded with the purpose, followed by a clean Args list and a Returns line. It contains no filler or redundant information.

  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 simple read-only sampling tool, the description provides enough to make a correct call: parameter semantics, default value, and return type. The main gap is that the sampling strategy is not specified, which could lead an agent to misunderstand how the sample is chosen.

  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%, but the description names and explains all three parameters in the Args section, including file_path, variable_name, and max_samples with its default of 100. This fully compensates for the schema's bare property definitions.

  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: "Extract a sample of actual data values from a variable for inspection." It clearly distinguishes from siblings like get_variable_info and get_variable_stats, which summarize or describe variables rather than return raw values.

  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 "for inspection" implies the tool is for exploring actual data values, but it never says when to prefer this over get_variable_stats or get_variable_info, nor does it mention alternatives. Usage guidance is left to inference rather than being explicit.

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

• get_time_rangeA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description takes on the responsibility of disclosing behavior. It states that the output is a JSON string, that the result is human-readable, and that CF time coordinates with various calendars are handled. It could mention error cases for non-CF or missing time dimensions, but the disclosed behavior is adequate for a read-only inspection 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 appropriately sized and structured with purpose, behavior, Args, and Returns. Every sentence contributes information, and the key purpose 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?

  For a simple one-parameter inspection tool with an output schema available, the description covers the essential invocation path and expected output. It is not fully complete because it omits edge-case behavior and any comparison to sibling tools, but those are minor gaps at this complexity level.

  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 coverage is 0%, so the description must define the parameter. It does: 'file_path: Path to the NetCDF file.' This adds essential meaning beyond the bare string type, though it is minimal and lacks examples or constraints.

  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 and resource ('Get the time range of a NetCDF file') and adds scope ('human-readable format', CF-compliant time coordinates). This clearly differentiates it from sibling tools focused on spatial bounds, variable listing, or dimension values.

  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?

  Usage is implied rather than explicit: an agent can infer this tool is for obtaining a time range summary, but the description does not say when to prefer it over alternatives such as get_dimension_values or check_cf_compliance. No exclusions or when-not-to-use guidance is provided.

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

• get_dimension_valuesA
  4.6/5.0
  Behavior4/5

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

  Since no annotations are provided, the description carries the full burden of behavioral disclosure. It states the return format ('JSON string with dimension values') and the default cap of 100 values, which implies truncation behavior. It could go further by describing error handling or behavior for missing dimensions, but the core read-only behavior is disclosed.

  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 compact and well-structured: a one-sentence purpose statement followed by a clean Args and Returns block. Every line adds value, and no information is repeated unnecessarily.

  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 simple read-only lookup tool with three documented parameters and an output schema, the description fully covers what is needed to invoke it correctly: file path, dimension selection, result limiting, and return format. There are 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?

  The schema has 0% property-description coverage, so the Args section is the only source of parameter meaning. It clearly documents all three parameters: file_path, dimension_name, and max_values, including the default value.

  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 'Get values along a dimension' and gives concrete examples like 'time steps, lat/lon coordinates', clearly identifying the action and resource. This differentiates it from sibling tools like get_variable_stats or get_time_range, which target variable data or ranges rather than dimension values.

  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 examples establish a clear context for when to use this tool: retrieving actual dimension/coordinate values rather than variable data or bounds. It does not explicitly name alternative tools or state when not to use it, so it does not reach the highest level of guidance.

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